Unlock customer insights: ADA's Unified Customer Views inform Lotte Rental's service development
The Results
Established a robust infrastructure for the following purposes:
- Managing crucial driving safety-related information
- Development of safety driving score: Identify the driver’s persona based on driving scores
- Segmentation: Customer profiles help facilitate marketing segmentation and inform new service development initiatives.
- Personalisation: This integration plays a pivotal role in dynamic pricing strategies, where pricing adjustments are tailored based on the identified risk types associated with driving behaviours.
- Enhance service quality and optimise overall business operations based on customers’ driving patterns
The Execution
Lotte, a major conglomerate in South Korea, comprises over 90 business units spanning diverse industries. Lotte Rental, a subsidiary, manages a range of equipment including automobiles, communications devices, and construction equipment, catering to a broad spectrum of needs.
Despite possessing a substantial volume of IoT data generated from the vehicles they rent, showcasing varied driving patterns, this data remained isolated in silos. Hence, there is a need to establish an environment that facilitates the analysis of this extensive dataset while ensuring its integration with other customer-centric data.
The client seeks a solution to unlock the potential of driving behaviour data, exploring ways to understand customer preferences and identifying practical business use cases that can enhance operational efficiency and customer experience.
The Approach
Treasure Data CDP emerged as the optimal solution, particularly excelling in establishing customer-centric integrated data and seamlessly handling vast behavioural datasets. Recognised as the premier CDP platform for analysing extensive datasets with exceptional flexibility, TD CDP became the cornerstone of our strategy.
ADA led the design of the solution’s architecture, system, and data structure. The implementation phase involved configuring the CDP settings and Extract, Transform, and Load (ETL) processes. Custom analytics was crafted and presented through intuitive dashboards, introducing a new perspective to customer insights. For example:
- Frequency of refuelling petrol: Anticipating potential risks such as running out of fuel, by understanding refuelling patterns.
- Driving location pattern: Discerning drivers' habits, whether they prefer nighttime driving, dawn journeys, extensive city-wide trips, or routine trips between home and grocery stores.
- Point of interest: Identifying travel locations and destinations to pinpoint hotspots.
All the newly extracted customer characteristics are integrated into the customer profiles, facilitating marketing segmentation and informing new service development initiatives. This integration plays a pivotal role in dynamic pricing strategies, wherein pricing adjustments are tailored based on the identified risk types associated with driving behaviours.
.webp)
