Back to Portfolio

Recommendation System for Spare Parts and Services

Recommendation System for Spare Parts and Services

Overview

For Toyota Astra Motor, after-sales service goes beyond basic maintenance—it’s a chance to strengthen customer relationships and offer helpful products at the right moment. To support this, Teman Data built a smart system that predicts which customers are likely to return on time for routine service. This helps the team plan better and stay ahead of demand. The system also highlights upsell opportunities, making it easier to match customers with products or services they actually need. By combining smart predictions with practical insights, Toyota Astra Motor was able to improve service quality and unlock more value from every customer visit.
 

Challenge

Toyota Astra Motor used to face challenges in predicting customer behavior around service visits. Some customers showed up on time, while others postponed or missed their appointments, making it hard to plan staff and resources effectively. Upselling products and services after maintenance was also tricky—it mostly depended on guesswork rather than clear data. As a result, the team missed chances to offer the right products, struggled to keep customer engagement consistent, and found it difficult to know which customers to focus on.
 

Solution

To solve these challenges, Teman Data built a smart system that helps Toyota Astra Motor understand customer behavior more clearly. By grouping customers based on how often they come in, how recently they visited, and how much they spend, the system could spot patterns and predict who’s likely to return for routine service. It also highlighted which customers were most valuable and where upselling opportunities made sense.

This gave the team a clearer way to plan ahead—knowing who to expect and how to engage them better. With these insights, Toyota Astra Motor could improve service punctuality, offer more relevant products, and boost after-sales revenue through smarter, more focused customer outreach.
 

Output

  • Implemented data preprocessing pipeline using Azure Machine Learning Studio
  • Developed a machine learning and business formula for recommending the product during maintenance service
  • Analyze which kind of customer that has been punctual for maintenance services
     

Impact

  • Minimize the time for preprocessing and gathering data from different sources
  • Improving the upsell product during maintenance service
  • Reducing the non punctual customer for maintenance service
     

Ready to go further with Teman Data?

Smarter care, fewer delays. Teman Data unifies patient, staff, and resource data to cut wait times, boost efficiency, and improve outcomes.

Tailor solutions to your goals, making data simple, scalable, and truly actionable.

logo

©2026 Teman Data. All Rights Reserved