Machine Learning with Decision Trees and Multi-Armed Bandits: An Interactive Vehicle Recommender System

2019-01-1079

04/02/2019

Event
WCX SAE World Congress Experience
Authors Abstract
Content
Recommender systems guide a user to useful objects in a large space of possible options in a personalized way. In this paper, we study recommender systems for vehicles. Compared to previous research on recommender systems in other domains (e.g., movies or music), there are two major challenges associated with recommending vehicles. First, typical customers purchase fewer cars than movies or pieces of music. Thus, it is difficult to obtain rich information about a customer’s vehicle purchase history. Second, content information obtained about a customer (e.g., demographics, vehicle preferences, etc.) is also difficult to acquire during a relatively short stay in a dealership. To address these two challenges, we propose an interactive vehicle recommender system based a novel machine learning method that integrates decision trees and multi-armed bandits. Decision tree learning effectively selects important questions to ask the customer and encodes the customer's key preferences. With these preferences as prior information, the multi-armed bandit algorithm, using Thompson sampling, efficiently leverages the user’s feedback to improve the recommendations in an online fashion. The empirical results show that our hybrid learning method can effectively make interactive vehicle recommendations to users.
Meta TagsDetails
DOI
https://doi.org/10.4271/2019-01-1079
Pages
10
Citation
Yu, T., Mengshoel, O., Meroux, D., and Jiang, Z., "Machine Learning with Decision Trees and Multi-Armed Bandits: An Interactive Vehicle Recommender System," SAE Technical Paper 2019-01-1079, 2019, https://doi.org/10.4271/2019-01-1079.
Additional Details
Publisher
Published
Apr 2, 2019
Product Code
2019-01-1079
Content Type
Technical Paper
Language
English