Download PDF
DataRobot Helps D&G Find Success When the Price Is Right
Technology Category
- Analytics & Modeling - Predictive Analytics
Applicable Functions
- Business Operation
- Sales & Marketing
Use Cases
- Predictive Replenishment
Services
- Data Science Services
The Challenge
Domestic & General (D&G), a specialist in providing warranties for household appliances, was facing a challenge in personalizing and delivering relevant offers to its customers. With 9 million customers in the UK and 16 million globally, the company was resource-constrained for the scale of personalized customer service and offerings they were trying to reach. The company's pricing team had to build a lot of models for each customer, which was a laborious and time-consuming process. D&G wanted to predict the likelihood of churn when customers are up for renewal and determine the price point at which customers are most likely to be happy with the warranty coverage they receive and renew their policies. However, delivering this level of personalization to individual customers required building a lot of pricing models, which was not scalable with their existing resources.
About The Customer
Domestic & General (D&G) is a company that specializes in providing specialist warranties for household appliances. The company has been in operation for over 100 years and is headquartered in the UK. D&G has more than 16 million customers in 14 countries and protects over 200 different types of electrical items. The company focuses on customer satisfaction and personalization, making it the largest appliance and gadget insurance company. D&G offers more coverage than other warranty providers and aims to deliver personalized and relevant offers for complementary services and products that make sense for each customer.
The Solution
D&G turned to DataRobot's automated machine learning platform to automate the building of their predictive machine learning models. The company launched a POC engagement with DataRobot at the beginning of 2017, testing a price optimization approach with the DataRobot API. The POC delivered more accurate models in less time than the status quo in R. Once they got buy-in and security approval to move forward with the cloud, D&G was up and running and ready to optimize pricing for all its customers. Now, all of their pricing models are built in DataRobot and fed into D&G’s price optimization system. For each customer, D&G’s pricing system makes a call to DataRobot and identifies the customer’s profile. DataRobot then spits out 200 price points for each customer, with a prediction at each price point. The system then identifies the optimal price where the customer will most likely renew and be happy with his service and delivers that to him at the time of renewal.
Operational Impact
Quantitative Benefit
Related Case Studies.
Case Study
Designing an intuitive UI for effective product demand forecasting in retail
The client, a leading luxury store chain operating in over 100 countries, was facing challenges with their product demand forecasting process. The process involved a significant amount of manual work, with all sales-related data being kept in Excel tables and calculated manually. The client's merchandising and planning experts used a demand forecasting web application to make estimations of customer demand over a specific period of time. The solution calculated historical data and other analytical information to produce the most accurate predictions. However, the client wanted to improve the efficiency and effectiveness of this process, making it faster, more accurate, and less complicated for their employees. They sought to unify all processes under an intuitive UI.
Case Study
Blue Bottle Coffee Enhances Ordering Accuracy and Reduces Waste with ML-Driven Demand Forecasting
Blue Bottle Coffee (BBC), a global coffee roaster and retailer, faced a significant challenge in managing the supply of pastries across its international network of cafes. The company was using a manual ordering system, where cafe leaders estimated the required quantity of pastries based on historical sales data, current inventory, and growth projections. This system was effective when BBC had a few cafes, but with over 70 cafes worldwide, it became inefficient and inaccurate. The inaccuracies led to either under-ordering, causing sell-outs and customer dissatisfaction, or over-ordering, resulting in food waste and profit loss. The suboptimal utilization of pastries was also affecting BBC's bottom line. Therefore, BBC needed a scalable, precise, and predictive ordering solution to improve pastry ordering accuracy, reduce food waste, and meet its sustainability goals.
Case Study
Optimizing delivery of global educational programs with deeper insight into company finances
EF Education First (EF) provides language tuition around the world, often by immersing students in another culture. As student numbers fluctuate in different markets and destinations, the company must manage a dizzying array of costs relating to staffing, accommodation and educational materials, and price its offerings to maintain healthy profits while also maximizing sales. With thousands of employees influencing its budgets and financial plans, the company had difficulty ensuring a consistent approach to calculating costs and collecting data. Historically, EF had relied on spreadsheets to collect and compile financial and operational planning data from employees. As a highly decentralized organization, this was no easy task, and it was difficult to ensure a standardized approach to calculating figures and creating accurate budgets.
Case Study
Erhvervsstyrelsen: Automating financial planning processes and building budgets that everyone believes in
Erhvervsstyrelsen, the Danish Business Authority, supports businesses across Denmark. It runs 450 projects across 27 offices, employs 600 people, and is responsible for an annual budget of DKK 600 million (USD 89.8 million), as well as a number of national and EU grants. Each of these projects manages its own budget – but Erhvervsstyrelsen needs to maintain control of overall expenditure, report back to the Danish parliament, and demonstrate the value it delivers for taxpayers’ money. For this reason, it is very important for the organization to have a robust, reliable budgeting process. Erhvervsstyrelsen was formed by a merger of three former agencies, each of which had its own separate budgeting system. Since none of these systems could be adapted to meet the needs of the new organization, Erhvervsstyrelsen set up a new budgeting process based on spreadsheets. This process involved sending out spreadsheets to each project manager, and manually collecting and consolidating the data they sent back.
Case Study
Getin Noble Bank S.A. Personalizing offers to meet customers’ specific banking needs raises savings deposits by 20 percent
Getin Noble Bank S.A. experienced several years of rapid growth, at twice the pace of the rest of the Polish banking sector. As the market became saturated, customers demanded a higher level of service. To create tailored product offers to meet their needs, the bank needed a more efficient and automated method of customer segmentation. It also wanted to develop effective campaigns with repeatable and predictable results.
Case Study
SmarterData: Helping retailers redefine practices for the digital age
SmarterData, a company based in San Ramon, California, wanted to help its clients navigate the uncertainties of the digital-age retail industry. The company aimed to find new ways to provide relevant, actionable, data-driven insights into consumer behavior. As the online retail sector continues to grow, many traditional retailers find themselves struggling to keep pace. In today’s digital economy, companies of all shapes and sizes must both manage and exploit digital transformation in order to survive. SmarterData offers a range of predictive and prescriptive analytics services – including innovative mobile apps that help consumers find products, and retailers gain real-time insight into store operations.
