Vehicle Recommendation System using Hybrid Recommender Algorithm and Natural Language Processing Approach

Abstract

Owning a vehicle has become a mandatory requirement in the modern world. Automobile industry investing a lot on producing different car models to cater the needs of their customers with different social and economic backgrounds. Thus, Auto makers constantly produce similar car models with different features. In Sri lanka, total number of new vehicles registered at Sri Lanka Registry of Motor Vehicles(RMV) during the period of seven years (from 2008 to 2015) has been increased from 265,199 to 668,907 which is nearly 2.5 times growth. This figure shows the rapid growth of the domestic vehicle market. For a new customer, choosing the most appropriate vehicle requires an extra effort/time and has become a challenging task. For example, matching personal interests and economy with number of available options is a quite complex task. Thus, most of the customers seek support from experts who provide consultancy services. However, customers frequently making complains about the existing services which offers consultancy for new vehicle buyers. The key issues are the people involved in the consultancy are not technically sound and pay minimal attention to customer requirements. Their main focus is to sell the vehicle. Thus, the customers face numerous difficulties before and after buying their vehicle. To address this problem, this research presents a novel vehicle recommender system which guides and gives suggestions to the customers using machine learning technologies. Here, we trained a neural network model using data collected from vehicle users and vehicle sellers. Other than the neural network model, the proposed recommendation system uses natural language processing (NLP) to produce more personalized recommendations. The results shows that the recommendations made by the proposed vehicle recommendation system achieves 96% accuracy in recommending vehicles.