Case StudyPartner Page

Read about how we used Custom Recommender Systems to help the Chief Technology Officer and product team at a corporate training solutions provider. Our client wanted to improve the way customer success representatives recommended content to customers. We created models in a Python notebook to identify patterns in data and personalize customer experiences and recommendations. We delivered a ready-to-deploy solution for our client to integrate into their products.


A fast-growing company in the corporate training industry provides its customers with an online content marketplace to buy courses. When onboarding new customers, the client’s customer success reps manually provide recommended content based on their intuition. Our client wanted to scale this process so that customer success reps offer better and faster recommendations using a data-driven approach.


Synaptiq developed a series of models in a Python notebook that solve the cold start challenge for new customers and new courses. This entailed:

  • Identifying similar customers to the newly on-boarded customer
  • Finding courses used by similar customers
  • Finding courses that are like the courses used by similar customers
  • Ranking the resultant list of recommended course

Course similarity was computed using NLP methods based on course abstracts. We used dimensionality reduction methods to project courses and customers into a latent space in which the sparse metadata we had in the cold start case could be used to compute measures of similarity.  Supervised machine learning methods then tuned weights to build a model that accurately predicted the rating a customer would give for any course.

How Custom Recommender Systems Helped

While we set out to solve only the cold start problem, we also provided a solution for recommending courses to existing customers so that the client could also use the recommender system after onboarding.  We provided the client with two Python notebooks for them to integrate into their applications. They plan to roll out the recommender system to their customer success reps late this summer.