Data Science: A Profit Center

When you’re tasked with creating a global analytics capacity from scratch, where do you start? At Inchcape, a £8.1B auto distributor, it began with a plan.

Alex Capewell, Director, Global Data and Analytics, and his small team set out to build a centralized analytics group serving more than 40 countries across the globe. The leading independent, multi-brand automotive distributor operates on six continents with brand partners such as Toyota, Mercedes-Benz, and BMW. 

The goal was to zero in on high-value models that the team could scale to support business decisions globally. For that, the group needed to build the tech stack and team, and implement AI.

“We wanted to leverage technology to help us go faster and manage hundreds of models, without accelerating costs,” Capewell said.

Fortunately, the business believed in the potential of analytics to deliver real value.

From day one, we viewed data science not as a cost center but as a profit generator.

Nearly 50% Faster from Experimentation to Production

For the core of its tech stack, Inchcape began with a global data warehouse using Microsoft Azure. The company chose Databricks for data preparation and BI calculations, and initially, used Python notebooks for analytics. The entire architecture is based on Lakehouse. For images in particular, they rely on Google Cloud Platform.

Inchcape deployed the DataRobot AI Platform as an essential piece of its scaling strategy. Critically, DataRobot connects via APIs with the company’s technology ecosystem and the legacy systems acquired through occasional acquisitions.

Toward Inchcape’s scalability goals, DataRobot brings automation to the entire AI lifecycle. On the front end, Inchcape notes it now runs proofs of concept in less than half the time, helping them arrive at a viable model or move on to another one faster. Expediting experimentation, the team at DataRobot partnered with Inchcape to create a single model that could be trained, scaled, and repeated for each business.  

“What we find really valuable with DataRobot is the time to value,” Thilak said. “We can test new ideas to quickly determine the value before we scale across markets. Now, DataRobot helps us deploy an end-to-end solution in a market within weeks, as well as manage the entire AI journey.”

Inchcape’s brand partners notice and appreciate that agility.

Where I think we’ve really set ourselves apart is the speed and the scale that we’ve managed to deploy across countries, geographies, OEM partners, and brands. When we share the scale that we’ve deployed with our manufacturers, they’re flabbergasted. Once we have the data, the speed to market of a new solution is something they’re always super impressed by.

Visibility within DataRobot aids in model explainability for the business and partners. The interface easily shows the sensitivity of changes to parameters.

Optimizing Pricing in One-Quarter the Time

As Inchcape has enriched its team, it finds DataRobot empowers data scientists to assess value quickly, deploy models to production, and monitor them—in one place.

The speed to market with DataRobot is super fast and it scales our data science efforts. We can improve both the efficiency and effectiveness of our data scientists.

The analytics team at Inchcape has now grown from five to 230 people globally. With more than 100 models in production, they enhance decisions across the business:

Optimizing pricing—DataRobot helps identify the best pricing across thousands of SKUs for vehicles and spare parts. Previously, Python coding for this took about 16 weeks. Now, it’s down to three to four weeks, the team reports.

“We can get more accurate pricing that helps improve margins,” Capewell said. “It’s probably been our biggest win as a business using DataRobot.”

Churn prediction—The company identifies customers at higher risk of churn and the reasons why, and proactively reaches out. That’s helped drive a double-digit uplift in customers attending out-of-sale workshops, according to Inchcape.

Lead scoring—Inchcape taps into all data about customers to score leads, anticipating the type of vehicle they might buy and their likelihood to buy. “Lead scoring was one of our first use cases,” Capewell said. 

Demand forecasting—Inchcape created a new model to anticipate demand for parts, topping one previously built by a consultant.

“We gave DataRobot to one of the new members on our team,” Capewell said. “Within two or three weeks, he came up with a model that was significantly more accurate. It’s a testament to the power of DataRobot to get models to market faster than ever, with fewer resources and less cost.”

A Partnership for Continued Value Delivery

Next, the team looks forward to taking their analytics practice further with DataRobot’s custom inference metrics. By adding their own KPIs to the metrics provided by DataRobot, they can fully track model performance. When they identify a more accurate challenger model, they can replace it – ensuring they continuously improve model quality.

And they expect generative AI to further improve efficiency and business outcomes, from coding to explainability to visualization. DataRobot uniquely combines predictive and generative AI so that companies can make predictive data more easily consumable, via chat interfaces for example. 

They expect generative AI to further accelerate and extend their efforts. New use cases are expected to drive even greater efficiency and business outcomes, from coding to explainability to visualization. And, since DataRobot’s AI Platform uniquely combines predictive and generative AI, customers can make information from their predictive models more easily consumable to more people with easy chat interfaces. 

Inchcape sees its partnership with DataRobot as integral to its continued value delivery.

“DataRobot’s partnership has been first class and really helps us accelerate,” Capewell said. “We have very ambitious deployment plans and there’s no way we could have gotten where we have without DataRobot on our side.”

The post Models Launched 50% Faster at £8.1B Global Auto Distributor appeared first on DataRobot AI Platform.

DataRobot is our AI platform of choice, which gives us the unique ability to identify, communicate, and engage with our consumers through highly personalized touchpoints. We’re doing things like AI-powered recommendations, optimizations, and direct signals that our dealers, retailers, product partners, and Ford’s digital marketing teams rely on.

FordDirect: An Indispensable Marketing Partner

In the competitive vehicle market, dealers who can anticipate when consumers are ready to buy have an edge.

For Ford Dealers and Lincoln Retailers in North America, a unique partnership makes that possible. FordDirect, a joint venture between Ford Motor Company and Ford Dealers and Lincoln Retailers, serves as their trusted advisor and digital marketing solution provider.

“There really is nothing like FordDirect in the automotive industry,” said Tom Thomas, Vice President of Data & Analytics at FordDirect. “Our mission is to be an indispensable partner to the dealers and retailers and drive more sales and service for them and Ford.”

AI for More Personalized Customer Experiences

FordDirect launched its Customer Journey Platform with the goal of creating a 360-degree view of the customer journey. The platform captures thousands of customer signals – from web visits, calls, chat interactions, and other touches – across Ford, dealers, retailers, and third parties in near real-time.

To help make sense of the data, FordDirect relies on the DataRobot AI Platform, which integrates with Microsoft Azure and Databricks.

“DataRobot is our AI platform of choice. Together with our Customer Journey Platform, we have a unique ability to identify, communicate, and engage with our consumers through highly personalized touchpoints,” Thomas said. “We’re doing things like AI-powered recommendations, optimizations, and direct signals that our dealers, retailers, product partners, and Ford’s digital marketing teams rely on.”

Marketing and advertising partners tap the insights to create more personalized experiences for current and prospective customers.

From Start to Implementation 75% Faster

As FordDirect and its data science partner RXA @ OneMagnify tackle each step of the data science process, DataRobot automates the machine learning process. The platform helps prepare data, determine features, move models into production, validate them, set governance rules, and monitor and measure models to improve continuously.

On the front end, DataRobot connects to FordDirect’s data platforms to help prepare the data. Automatic data readiness checks assess data input, saving data scientists time. Then, the platform automatically derives hundreds of features to use.

“One of the things I love about DataRobot is the ability to actually model against different feature sets,” said Jonathan Prantner, Chief Analytics Officer at RXA @ OneMagnify. “You can model against all the features plus the ones that DataRobot has derived, or use the platform’s predictive powers regarding which features are most important.”

Then, DataRobot automatically trains potentially hundreds of models, enabling data scientists to zero in on the winning ones.

Once in production, the platform provides detailed insight into model performance. Data scientists spend less time on maintenance and more time on new projects.

DataRobot automates every phase. Data scientists can actually focus on data science, turning one data scientist into four. And that’s not a number that we are just throwing out there. Compared to a custom hand-developed model, from data access to implementation, it takes one-fourth the time.

Finding Prospects 18X More Likely to Buy

FordDirect runs several large-scale models for use cases such as forecasting, multi-touch attribution weighting, media mix modeling, customer and dealer/retailer segmentation, natural language processing, and propensity scoring.

One of its top-performing models identifies customers with a likelihood to purchase within the next 90 days. Using this propensity model, FordDirect found that the highest-scored leads are 18 times more likely to buy a vehicle. In fact, 90% of all buys happen in the top 20% of scored customers – a segment valued at an impressive $6.5 million.*

Moreover, they find that model performance is five times faster than the original model, allowing the company to score more customers and service vehicles over time at the dealerships.

Ultimately, this model and others help FordDirect score records to create journey profiles regarding propensity to buy and service, and other preferences and predictions to determine next-best actions.

“We continuously feed these individual customer signals into DataRobot’s automated machine learning platform to calculate and refine each customer’s likelihood to purchase or conduct service over the next 90 days,” Thomas said.

Testing and Monitoring New LLMs with Generative AI

By adopting DataRobot in combination with the Customer Journey Platform, FordDirect was able to replace legacy technology systems. This move decreased their technology debt by approximately $3 million* – all while improving agility, efficiency, and effectiveness.

Next, FordDirect looks forward to scaling with generative AI use cases to add additional value, and unifying workflows for both predictive and generative AI. The platform offers the ability to test and try new large language models quickly, and rapidly build, securely operate, and confidently govern the performance of those LLMs in one place.

It also helps the company safely extend its proprietary data with LLMs and maintain ownership over its intellectual property as it continues to deliver value to Ford, Lincoln, and their dealership networks.

“The combination of DataRobot and FordDirect has really given our dealers and retailers an advantage in the marketplace in terms of increased sales, service, higher ROI, and stronger customer loyalty,” Thomas said. “What we’re able to do is unprecedented.”

*Figures provided by FordDirect based on their own experience.

The post FordDirect Uncovers AI-Powered Insights 75% Faster, Driving Sales and Service appeared first on DataRobot AI Platform.

Building an Innovation Team

Around the world, more than 75,000 organizations partner with BSI to improve the quality, safety, and integrity of their products, services, and systems. At more than 100 years old, the Royal-Chartered organization publishes around 2,700 industry standards annually in areas including environmental sustainability, digital trust, health and safety, quality management, and the eradication of modern slavery.

When Craig Civil joined the organization as Director of Data Science and Artificial Intelligence, his role was clear: build an AI-focused innovation team that helps BSI accelerate progress and deliver on its purpose. Aptly, he would do so at one of the world’s hubs of thought leadership, the Cambridge University Science Park.

As he created his team, Civil knew their software toolkit was key.

“We needed to transform the way we’re working and the products and services we offer to clients in order to build digital trust, and I knew that data science and AI were core components of that transformation,” Civil said.

Deploying an End-to-End AI Platform with DataRobot

In previous organizations, Civil often juggled multiple systems to get his job done. Data processing, quality checks, graphs and reports, stats and algorithms, and visualization and output each took place in separate applications.

With a budget to resource a new data science team and procure new software tools, Civil applied his experience from previous roles and identified the need for a unifying and transparent ML platform as a critical early requirement. Reaching out to several potential vendors, they contacted DataRobot.

The DataRobot AI Platform is the only open, complete AI lifecycle platform leveraging machine learning with end-to-end capabilities for both Experimentation and Production.

The first draw for me to DataRobot was having a platform that brings together all of the components to create a successful, robust model. From data ingestion to quality checks to automated algorithms, it’s an end-to-end solution.

Finding the Most Impactful Models Fast

From the start, Civil saw the value in the DataRobot Success Package, which gave them guidance from DataRobot data scientists through every step.

“It was as if the DataRobot team was part of my team,” he said. “They filled a temporary technical gap and supported me in succeeding as I recruited into my new team.”

As data scientists joined, they ramped up quickly on the platform via DataRobot University. 

Leading a growing data science team, Civil indeed finds having a single platform invaluable in optimizing the effectiveness and efficiency of their work. It brings the full flexibility to integrate with the company’s current ecosystem or use the API in the future. On the front end, DataRobot pulls data directly from Microsoft Azure, saving time and reducing the risk of errors in data transfer. They then view insights in Microsoft Power BI. 

When creating models, automation helps them choose the most impactful models faster. Plus, they can quickly see why one model performs better than another and offer documentation on those decisions if a client or BSI colleague asks.

Automation in DataRobot can save huge amounts of time. Not only that, but the platform recommends models that we might not have considered.

Uncovering Insights that Benefit Clients, Auditors, and Patient Safety

In BSI’s Assurance business, clients suggested that the more they know about their standards’ compliance performance relative to others in their industry, the happier they were. To help, BSI created a model to provide a predictive view into the likely outcome of their next audit and how that benchmarks across various indicators.

DataRobot helps us give clients insight into where they could focus scarce resources and prepare for their next audit in a more insightful way, in a trusted partnership with BSI.

Auditors also use those findings to understand where a client is relative to others in the industry and possible areas where the organization could focus resources to better mitigate business risk.

Additionally, the team is creating an ML solution to improve medical device safety. BSI receives reports of incidents related to medical devices from around the world. As data comes in, DataRobot helps make sense of it. If anything looks unusual, the model can trigger an alert to investigate it further.

“Proactively analyzing medical device data has the potential to help reduce failures and improve patient safety down the line,” Civil said.

Extending AI across BSI

Civil credits DataRobot for enabling his DSAI team to deliver trusted model predictions rapidly to internal and external clients.

“Having a single platform that pulls everything together can’t be underestimated,” he said. “Then there’s the combination of the technology and the collaborative DataRobot team. If either one of those wasn’t there, I would have looked elsewhere.”

At BSI, now colleagues across the business are taking notice of the impact of AI, leading them to reach out to the DSAI team.

“People are coming to us with their ideas and opportunities for applications of data science and AI,” Civil said. “With DataRobot, we have a framework to help them and ultimately help build digital trust.”

As BSI applies AI to its modern challenges, this century-old company is proving that age is no barrier to innovation.

The post AI at BSI: A Century-Old Company Brings AI Models to Production in One-Third of the Time appeared first on DataRobot AI Platform.

Modeling with Ease and Transparency

At Sanlam, one of Africa’s largest and oldest financial institutions, data analytics influence sales, improve client retention, help manage expenses, and support key strategic initiatives.

When Sanlam began applying AI to its analytics, open-source options felt cumbersome to navigate and lacked critical explainability for business stakeholders and compliance.

“With open-source software, optimizing a model could take anywhere from two weeks to a month,” said Shabbeer Omar, Head of Advanced Analytics (Business Intelligence) at Sanlam. “And we needed to be able to explain the dynamics underlying the model build and its predictions.”

Accessible AI for Actuaries and Data Scientists

After engaging with the DataRobot team and its AI Platform, Sanlam immediately saw the potential for end-to-end automation to expedite and expand its AI efforts for both data scientists and actuaries. Through a managed cloud environment, the company uses the platform’s best-in-class MLOps capabilities, including model performance monitoring.

“What blew us away was the ease with which the AI Platform makes data science and machine learning accessible to everyone,” Omar said. “The slick interface really streamlines the model-building process, where DataRobot builds models using multiple machine learning algorithms and automates the optimization process for each ML algorithm given the data. This automation of the technical model build allows our team to focus on solving the business problem at hand.”

Omar and the team also appreciate the flexibility of the platform’s multiple AutoML deployment options, including a JavaScript embedding approach as well as an API integration between Sanlam and DataRobot.

With MLOps, they can monitor models in production for data drift and can see the features driving each model much more easily. By understanding those underlying data points, Sanlam can deliver essential explainability to stakeholders.

“Understanding how various data points contribute to the outcomes of the model is so important for us to establish transparent processes in the business,” Omar said. “We can easily show that our decision-making is traced back to the data.”

Increasing Sales, Lowering Lapses

At Sanlam, sales performance depends on the quality of the leads it delivers to its customer-facing intermediaries. Using the DataRobot AI platform, they shifted lead qualification to be more data-driven. They also understand the features behind the leads, which influence customer retention and marketing efforts as well.

The performance of our data-driven campaigns far exceeds that of marketing campaigns where leads are based on intuition. We find clients with a higher propensity to purchase a given product having two to four times higher conversion rates relative to clients with lower propensities to purchase. This allows us to select leads more intelligently for campaigns.

For customer retention, they merge the company’s historical experience and the platform to create lapse propensity models. The earlier Sanlam can identify customers at risk, the sooner they can enact a range of interventions.

By spotting the factors that influence at-risk customers, Sanlam found that something as simple as a welcome message can positively influence customer lapse rates.

“We’ve seen improvement in lapse stats across our risk business,” Omar said.

Models One Month Sooner

The AI Platform transforms predictive analytics at Sanlam by simplifying the onboarding of new data scientists and empowering actuaries.

“We’re finding more actuaries in traditional spaces wanting to move into data science,” Omar said. “Since bringing in the platform, we’re exposing them more to the exciting world of advanced analytics.”

All users find they have shifted from manual coding to solving business problems, with a focus on understanding the variables that affect outcomes.

“Our role as data scientists or actuaries is not merely to write complex code or build dashboards,” Omar said. “The key role that we play is to focus on solving complex business problems through data—and that’s the most critical factor that DataRobot enables.”

Before, creating models took up to a month. Now, they find the same model creation process takes only a couple of hours.

From the start, the team at DataRobot has gone above and beyond in providing both technical and hands-on how-to help to guide Sanlam in approaching their industry-specific use cases, measuring success, and increasing adoption.

The post At Sanlam, South African Financial Institution, AI Helps Attract, Retain More Customers appeared first on DataRobot AI Platform.

The Limits of Conventional Analytics

Over the last 50 years, Freddie Mac has helped people realize their dream of owning a home more than 80 million times. The company has funded $11.6 trillion in mortgages and financed $6 million in rental units.

In 1970, Congress chartered Freddie Mac to support the U.S. housing finance system. Rather than lending directly to borrowers, Freddie Mac buys loans from approved lenders.

As market and economic conditions change, Freddie Mac must remain flexible and continuously deliver on its commitment to affordable, adequate housing. In a sea of unstructured and semi-structured data, it’s challenging to achieve meaningful predictions and key insights to inform business decisions. Working with hundreds of thousands of customers, and mining nearly four terabytes of data, they found business intelligence and manual practices didn’t scale.

Making Sense of Data – More Quickly and Accurately

Freddie Mac turned to the DataRobot AI Platform to automate predictive analytics from data input through managing models in production. The result: rapid insights that drive its mission.

“With DataRobot, we can analyze these large, complex datasets and gain valuable insights more quickly,” said Lakshmi Purushothaman, Vice President, Innovation in Data Science, Engineering, and Analytics.

The analytics team creates models that span across the organization, bringing value to internal teams, lenders, and their end customers.

As Freddie Mac collects front-end information from lenders and their customers and analyzes housing markets and properties, AI helps the business make sense of the data. The platform extracts data elements from various text documents and images much more quickly and accurately than with the previous manual approach.

Increasing Analytics Team Productivity by 2.7X 

The agency modernized its AI and ML infrastructure, shrinking the MLDev and deployment cycle to deliver meaningful value to the business rapidly. The DataRobot platform helps Freddie Mac rapidly home in on the winning models. 

Ultimately, the Freddie Mac analytics team attributes significant efficiency to the platform:

• 2 to 10 times faster proof of concept
• 1700+ hours saved in model development time per analytics project
• A 2.7X productivity gain for a corresponding jump in time to market

This efficiency means that the data science team can focus on more use cases and scale more readily.

“Our ability to leverage data science to help us identify disparities, remove barriers, and enable informed decisions from our data, which has been exploding in terms of variety, volume, and velocity over the years, has been made much easier with DataRobot,” Purushothaman said.

We’ve been able to shorten the life cycle of development from months to days today with the DataRobot platform.

“We’ve automated the stuff that data scientists didn’t really like doing so they can focus on what really drives change,” added Aravind Jagannathan, Chief Data Officer. “AI/ML has been critical in terms of the efficiency we’ve achieved by allowing us to scale massively.”

Managing Governance and Explainability with an AI Center of Excellence

The DataRobot AI platform offers essential interpretability and explainability for stakeholders and compliance teams. The team saves time and work because the DataRobot platform collects the needed documentation—available in one-click reports. Explainability tools help clarify AI models into business-speak, detailing what’s behind the models.

To promote model governance and manage risk, the Freddie Mac team also created an AI Center of Excellence (CoE). Among its roles, the CoE ensures that the various people involved in analytics projects understand the governance required.

From the outset of the relationship to the current stage, data scientists work closely with the DataRobot team via office hours and deep-dive workshops to explore use cases and apply best practices throughout the process.

“When I think about how DataRobot has enabled us and supported us with our current use cases or ideas, it’s really tied to helping us with our objectives,” Jagannathan said. “From a customer perspective, I’ve found that’s rare in a partnership. It’s fantastic to bear the fruit of that relationship.”

Speed to Market at Lower Cost

As Freddie Mac looks ahead, the organization is optimistic about the power and potential of AI to drive its business goals.

“The value is ultimately making sure we’re oriented to the customer always,” said Tatyana Krol, Senior Director of Business Intelligence and Analytics. “We’re augmenting the decision-making with AI and letting people do what they’re best at. It’s definitely going to have a transformative value over the next several decades.”

We’re reducing the time and cost in the borrower and the lender experience when it comes to getting a mortgage. We allow more people to get into homes that they can afford and keep.

The post Freddie Mac Advances Affordable Housing Goals and More than Doubles Analytics Productivity with AI appeared first on DataRobot AI Platform.

The Need: More Models in Less Time with the Same Team

At fast-growing Cegid, the predictive analytics team must meet ever-expanding demand fueled by frequent acquisitions.

The French company offers cloud services and software solutions for accountants, small businesses, retail, and corporate clients serving 350,000 businesses across 150 countries. 

Cegid’s analytics team takes on a growing list of business challenges, including predicting the likelihood to get paid on invoices and the propensity of customers to add services. As with most companies, the greatest analytics challenge is creating more models in less time and minimizing the technical skills and resources required to do so.

“We wanted to reduce the need to code while also accelerating model development,” said Joao Henriques, Head of Credit Risk and Data, Cegid.

A One-Stop AI Solution

When he joined Cegid, Henriques saw the opportunity to bring in DataRobot. From his experience at a previous company, he knew it offered the one-stop capabilities the team needed to automate the analytics lifecycle end to end.

We wanted an all-in-one platform. DataRobot is a no-code solution that covers the full spectrum of developing, deploying, and managing models. I’m convinced this is the best tool in the market for us.

The company turned to Portugal-based Passio Consulting for support in deploying the platform and applying it to specific business decisions. Passio brings business intelligence, artificial intelligence, data warehousing, and data virtualization solutions to help its clients transform data into a competitive advantage.

At Cegid, the solution integrates with Amazon Web Services and the company’s data lake using application programming interfaces (APIs). Cegid then analyzes insights in Microsoft PowerBI and Excel.

Faster Decision-Making While Managing Risk

Cegid applies the platform primarily in its invoice factoring business. To help clients with cash flow, Cegid extends financing to them based on open invoices—rather than clients waiting 30 or more days for end customers to pay. For their service, Cegid keeps a percentage of invoice totals.

The company has modernized factoring by turning it into a one-click process for clients. Using the AI platform, Cegid gains the necessary end-customer details to decide whether to pay or deny the selected invoices.

With a Payment Prediction Model (PPM), they evaluate the probability of payment for each invoice. Analytics also help them set optimal interest rates. Those insights help them manage risk in their decision-making.

“We use machine-learning models to support decision-making on all individual deals that we are making in terms of our factoring business,” Henriques said.

They’re also exploring models to improve collections on those invoices, as well as others to assess the likelihood of Cegid clients to convert to factoring clients.

20% More Deals in One Year = €15 Million

With the model developed using DataRobot, Cegid increased the approval rate on factoring deals by 20% without increasing risk—driving significantly more volume in funded invoices last year.  

“We’re using AI predictions on payment probability for every decision on invoices,” Henriques said. “Increasing the number of deals by 20% amounts to approximately €15 million in additional annual volume.”

DataRobot was the perfect match for a small team looking to put more models into production. Cegid makes decisions, such as setting interest rates, with much greater accuracy and has already seen a payback on their investment.

Deploying Models in 50% Less Time

Using DataRobot automated machine learning capabilities, Cegid expedites model experimentation and development, allowing them to test scenarios quickly. Data scientists traded coding for time to refine their data and evaluate business problems.

Though some data scientists were initially skeptical about the platform, Henriques finds they have changed their opinions after seeing the productivity of AutoML firsthand.

We accelerated model development—cutting the time to deploy models in half. We can now use our resources on analytical studies and business intelligence.

Cegid looks forward to applying the platform to more business challenges in its factoring division and beyond and knows it can rely on the expertise at DataRobot to help maximize its results.

“When we have technical questions, we get a rapid response from our account manager,” Henriques said. “We have only positive things to say about DataRobot support.”

The post French Tech Leader Cegid Generates €15M Additional Volume Annually with AI-Driven Decisions appeared first on DataRobot AI Platform.

Data Insights Demand, Limited Resources

At the insurance company MAPFRE, business lines rely on advanced analytics to help make decisions on pricing, sales, retention, underwriting, and more. The company operates in more than 100 countries across five continents, generating €27.3 billion annually.

Given the demand for data insights, it can be tough for the analytics team to keep pace with the many incoming requests and deliver value quickly.

“We needed to improve our time-to-market in evaluating the feasibility and impact of use cases to help decide if we should move forward,” said Diego J. Bodas, Director of Advanced Analytics at MAPFRE ESPAÑA.

Unlocking Analytics Productivity with AI

Weighing AI solutions, MAPFRE ESPAÑA chose the DataRobot AI platform to automate analytics and expand productivity in meeting business needs.

“DataRobot is a very mature solution that brought not only the technology but also knowledge and expert support,” Bodas said.

With a cloud-first strategy, the company relies on DataRobot APIs to integrate with Amazon Web Services, Microsoft Azure, and Amazon SageMaker, and an Athena driver links to the company’s data lake. Then they deploy models to Tableau and Microsoft Power BI for easy use by line-of-business employees.

Teaming with DataRobot engineers sped integration with the MAPFRE ESPAÑA cloud infrastructure and databases. Meanwhile, DataRobot Customer-Facing Data Scientists helped the MAPFRE team in Spain apply value-driven use cases to generate value quickly.

Automating Experimentation, Speeding Time to Value

By eliminating the need to hand-code models, the DataRobot platform expedites the time to explore and find promising new use cases. For each business challenge, MAPFRE ESPAÑA data scientists can rapidly experiment and evaluate multiple scenarios.

“DataRobot provides us with innovative ways to test new ideas,” Bodas said. “Given a problem and a dataset, DataRobot allows us to generate multiple prototypes 20% faster. And the process facilitates the learning evolution of our data scientists.”

“Programming in Python required a lot of manual work,” said Mario Encinar del Pozo, Senior AI Lead.

For us, it’s now very quick to get answers through deep-learning models with DataRobot. That kick-starts projects.

MLOps then simplifies deployment and offers a single spot to monitor models in production.

“For data scientists, it’s only a push of a button to move models into production,” Bodas said.

Fueling their agility, MAPFRE ESPAÑA empowers business users beyond the analytics team to create models on their own. Then, the analytics team tests and evaluates these models and provides those findings to business units.

We’re delivering insights that empower business units to make decisions that improve results.

AI Powers Personalized Premiums

MAPFRE applies DataRobot AI to business challenges companywide, including pricing premiums, sales, churn, underwriting, and fraud analysis.

The platform powers the price quoting engine for new policies. When customers seek a price quote, MAPFRE ESPAÑA needs to respond rapidly. Using the platform, the team produced 20 models to help determine personalized premiums for each customer.

And for a cross-selling model, DataRobot cuts the time to retrain models – a frequent requirement given changing economic conditions, new data, and data drift.

Given the regulatory nature of the financial industry, MAPFRE appreciates that, with a click, they can download the supporting compliance documentation for models. The compliance documentation satisfies legal concerns while saving time.

Agility to Face Changing Market Trends

With automated machine learning, the analytics team expands its capacity to serve the business and inform company-wide decisions. Throughout it all, DataRobot not only brings platform expertise but insights and best practices from a global customer base.

“From the first moment, Customer-Facing Data Scientists at DataRobot have responded quickly to support us in using the solution,” Bodas said.

The MAPFRE team in Spain looks forward to applying the platform to a growing list of use cases.

We expect DataRobot to provide us with more agility to face changing market trends. It equips the company with new competencies and allows us to keep fully up to date with the latest market developments.

The post Insurance Company MAPFRE Experiments 20% Faster with AI in Spain – Accelerating Business Value in Insurance from Pricing Premiums to Underwriting appeared first on DataRobot AI Platform.

To stay competitive and maximize profit, auto sellers strive to find that just-right price for each vehicle. Fortunately, it’s significantly easier when selling on one of Europe’s leading auction sites. AUTOproff provides a minimum price to sellers  in less than 20 minutes.

Every day, AUTOproff generates more than 1,400 car value estimates and offers sellers a minimum guaranteed price. If it sells below the minimum price, then AUTOproff covers the difference. The better the company balances the guaranteed price and the actual sale price, the more profit it retains from a sale.

Until recently, producing estimates has fallen entirely on a team of skilled vehicle professionals. But as the company has grown, scaling has increasingly become an important factor.

“Obviously there’s a huge scaling challenge with manual estimating,” said Jesper Bruun Hansen, Head of Data and AI. “Our team of estimators works seven days a week. When we wanted to grow the business, we knew we needed to do something else to ensure we maintain our promise to customers to deliver quotes within 20 minutes.”

Modeling “Automated from Beginning to End”

AUTOproff’s data science team leverages AI to speed estimating time. But with various machine learning solutions, the analytics team found it still needed to write a considerable amount of code and manually handle much of the modeling lifecycle. Most AI solutions it considered were too cumbersome for the small team to set up and manage.

In a proof of value with DataRobot AI Platform, however, the team was able to begin generating results with little setup and no coding.

“We wanted to find a high-availability platform we could trust for modeling and performance monitoring,” said Daniel Franch, Machine Learning Product Owner.

With DataRobot AI Platform, it was quite easy for our small team to use and quite fast from access to the first model in production.

From feature selection to model monitoring, DataRobot AI Platform eliminates the manual parts of AUTOproff’s analytics lifecycle. Where once data scientists were skeptical about DataRobot’s AutoML, they soon discovered it cut the time to arrive at optimal models.

“To be honest, we didn’t think we’d use AutoML much because that’s our main job as data scientists,” Hansen said. “But we now use it to deploy models and it’s automated from the beginning to the end.”

DataRobot MLOps simplifies monitoring models in production, enabling the team to stay on top of accuracy. Additionally, the platform has cut experimentation time dramatically. Instead of six months, they can now release models to production in three weeks or less.

“The whole experimenting phase now resides with just one data scientist where before three data scientists were actually doing that,” Hansen said.

Essentially, the platform automates the boring aspects of data science so the team can spend more time improving data quality, understanding stakeholders’ business challenges, and supporting the demands of moving into new markets.

Shorter Time to Quote

AUTOproff uses the AI Platform to create its Pricing Robot to support automated car value estimates. With a regression model, the company automates 55 to 60% of all estimates – benefiting customers, estimators, and the business.

We can provide an instant price for some cars and reduce the wait for customers. The average turnaround time for requesting a quote is shortened drastically.

With the AI Platform pricing more common vehicles, the company removes some of the tedious tasks for the company’s seasoned team of estimators. Now, they can focus on the more enjoyable, rarer vehicles – and can more easily get time off.

Moreover, the collaboration between data scientists and pricing specialists removes the intuition in pricing, resulting in more accurate prices that increase the chance that estimates will come closer to sales numbers.

Price Robots for New Markets

AUTOproff’s AI-driven Pricing Robot prepares the company for expansion across Europe, especially with the recent acquisition by AutoScout24. The team has confidence in its ability to meet its promises to customers, price as accurately as possible, and trust that the platform will be there reliably.

Our pricing robots are critical as we scale to the rest of Europe. We’re able to spin up quickly when going into new markets.

The post AUTOproff Automates More than 50% of Vehicle Estimates – Driving European Expansion appeared first on DataRobot AI Platform.

Operating for more than a century, NIM Group has grown into one of the industry’s most technologically advanced carbon steel providers. And to keep its edge, the company’s data analytics team looks for every opportunity to improve decision-making, from the factory floor to executive offices.

Ben Dubois, Director of Data Analytics, NIM Group, envisioned using data to improve functions such as quoting, inventory management, and even machine settings to improve scrap rates. For the latter, operators have typically relied on operators’ knowledge and experience, resulting in inconsistency and making it challenging to ramp-up new operators.

“We knew there were areas of the company where we could use data to add value, whether it’s improving accuracy in our decision-making, or being able to automate some of our decision-making,” Dubois said.

Rapid Time-to-Value

NIM brought in DataRobot AI Platform to automate predictive analytics and expand the team’s capacity to support the business.

“Other AI products were trying to solve a specific problem,” Dubois said. “What I like about DataRobot AI Platform is the ability to use it in any way you can think up, whether it’s a normal regression-type problem, or forecasting, or for many different use cases.”

In a proof-of-value project, with the help of DataRobot University and DataRobot’s Customer-Facing Data Scientists, Dubois was able to develop an accurate model and begin realizing value quickly. Just as important, he could see how their data affected the results – helping him explain models to business stakeholders.

Reducing Scrap Rates

DataRobot Data Prep helps automate prepping the data while AutoML creates advanced models. APIs then automate productionalizing the results on the shop floor. Then, they easily monitor models in production.

Among several applications, the company applies the platform to predicting machine settings for processing steel. By introducing the correct settings into the machine from the start of the process, they generate less scrap, thus creating significant cost-savings.

With the DataRobot AI Platform application programming interfaces (APIs), they gather information about jobs in real-time, run them through a model, and then feed optimal settings back to the machines. Completing the feedback loop, the company tracks the actual settings used and the corresponding scrap rates to refine the model further.

“By giving operators a starting point, we shorten the trial-and-error period,” Dubois said. “We’re making more accurate predictions over time. Our model will keep getting better and better.”

AI-derived machine settings deliver two key benefits: less experienced operators ramp-up more quickly and make more informed decisions. Secondly, NIM is able to generate more steel that can be sold rather than end up in a scrap yard.

As a commodity, steel can range from $500 to $1,000 per ton. By reducing our scrap rates and being more consistent job to job, we can generate significant annual savings for the business.

More Accurate Forecasting

NIM also applied DataRobot AI Platform to forecast demand for inventory to ensure they stock accordingly. For that, DataRobot Time Series allows them to find relationships between the demand for their steel and the industries they serve, such as agriculture and energy. By generating more accurate forecasts, NIM prevents lost sales and excess inventory, both of which are costly to the business.

“We look at factors within and outside the company so we’ll have the right inventory at the right time,” Dubois said. “One of the cool things about DataRobot and machine learning compared to just a normal time-series regression problem is being able to put a lot more features alongside your time series to make better forecasts.”

Models Months Sooner

NIM has generated business value from DataRobot AI Platform for years and only recently brought on a data scientist to help expand its efforts. By saving time across the process, Michael Green, Data Scientist at NIM Group, can spend more time with stakeholders to understand business problems and features.

“With DataRobot AI Platform, we don’t have to worry about the minutiae of building every detail of one model,” Green said. “Instead of taking weeks or months to go from raw data to a deployed model, now we can do that in less than an hour.”

As a data scientist, Green gains satisfaction from helping solve business challenges throughout NIM Group.

I enjoy helping people enjoy their work more, whether they’re saving time, saving money, reducing tedious tasks, or making better decisions. It’s meaningful and fun. DataRobot AI Platform is the best way for me to make an impact that actually matters for the people I work with.

The post Steel Manufacturer Reduces Scrap Rates – and Costs – with AI appeared first on DataRobot AI Platform.

An Ambitious Vision: Data-Informed Student Success

With 80 schools and 44,500 students across New South Wales, Catholic Education Diocese of Parramatta (CEDP) holds a trove of data on its students, from performance to attendance to demographics. 

And in that data, Dr. Raju Varanasi, Director, Data Intelligence, saw an opportunity. What if CEDP could mine it to predict outcomes such as student achievement or attrition and take steps to improve it? AI, he believed, was the answer.

“We have 400 dashboards on every aspect of our business,” Dr. Varanasi said. “To unlock that data, we wanted automated machine learning because we don’t have the budget for data scientists.”

94% Prediction Accuracy

CEDP turned to DataRobot AI Platform to automate its predictive analytics from end to end. The platform stood out for its essential explainability, documentation, and the fact that, as a stand-alone platform, it would plug into CEDP’s existing data sources, mainly Alteryx.

CEDP began applying AutoML to its primary targeted use case: predicting achievement for students in their last year of high school. For that, CEDP could tap into more than a decade worth of data. 

DataRobot AI Platform simplifies the entire lifecycle, from model preparation to building to monitoring. With DataRobot’s Automated Feature Discovery, they weighed 40+ variables before settling on 26 that were truly informative, including past student performance, attendance, and demographics.

The platform then runs through numerous models, enabling Dr. Varanasi and a small team of analysts to determine which one is the most effective. Dr. Varanasi also appreciates the ability to drill down into individual student profiles to understand why models scored them a certain way.

Predicting – and Influencing – Student Success

Using the DataRobot AI Platform, CEDP found that it can predict student achievement at around 94 percent accuracy. This gives teachers and administrators confidence in using those insights to help at-risk students, or guide others to meet or exceed their expected performance, or aid them in choosing the subjects where they’ll excel. 

“We are doing something fundamental that every parent and student would like to,” Dr Varanasi said. “That is to answer, ‘With my track record so far in schooling, where will I end up if I choose history, math, chemistry, or biology?’”

CEDP wasn’t sure how educators would respond to the insights. But they surprised Dr. Varanasi by asking if his team could predict achievement two years out instead of one – for an even further head start on helping students. 

“Once we explained to teachers that we’re complementing their efforts, not substituting their efforts, the resistance barriers came down, the adoption grew, and the goodwill about data has grown,” Dr. Varanasi said. “And that’s a very fundamental shift.”

“Predictive analytics helps to unearth current trends in courses and predict future performance,” explained Robert Nastasi, Principal at Emmaus Catholic College. “This data can help us focus on preparing the whole student, no matter what pathway they wish to pursue.”

Reducing Attrition, Retaining Revenue

In applying AutoML to another challenge, student attrition, CEDP pulled in a variety of features thought to influence attrition, including attendance, missed payments, student engagement, and awards. A post-attrition survey for parents helped identify some of these key factors.

By predicting the students that might leave, CEDP takes action to encourage students to remain at CEDP schools, such as offering tuition assistance or other forms of support. With the help of these findings, the school reduced its attrition rate by about 13 percent. By retaining more than 100 students that would otherwise leave, the school also preserved around 1.2 million dollars.

There is a discernible change in school exits. The benefits can be converted into monetary terms, which more than pays for DataRobot AI Platform.

With success with these two use cases, Varanasi is now turning to the platform to understand why Wi-Fi strength and reliability vary across schools. Getting ahead of outages could avoid considerable lost productivity.

Making a Difference Every Day

CEDP is applying predictive analytics to foster a data culture. Even before bringing in the DataRobot AI Platform, CEDP had hundreds of data dashboards. Progress with student achievement and attrition spur teachers and staff to stay committed to developing a data-informed culture.

Beyond that, machine learning empowers Dr. Varanasi’s team despite not having data science backgrounds.

“DataRobot is like having 150 data scientists under my desk,” Dr. Varanasi says. 

The predictions made through the use of DataRobot AI Platform make a difference in keeping students engaged, successful, and in CEDP schools. 

“We see value in DataRobot AI Platform,” Dr. Varanasi said. “We already see improvements in schools that have taken this to heart. Their curve is on the rise.”

The post Australian Schools Boost Student Success, Reduce Attrition by 13% – with AI appeared first on DataRobot AI Platform.