A Hybrid Laptop Recommendation System for Engineering Undergraduates
Aarush Acharya, Aditi Agarwal, Aisha Agarwal, Anshul Soni · 2023
Today, recommendation systems are widely used to solve the problem of finding the most relevant information from the abundant amount of data present. The literature findings suggest that there have been studies in various domains of recommendation systems such as skin care recommendations, movie recommendations, course recommendations, and others. However, limited studies exist on recommending products such as laptops which are a necessity these days and have become an important part of day-to-day life. From office workers to homemakers to undergraduate students this product is required by all. The undergraduate community faces challenges in identifying the right laptop due to lack of knowledge and expertise. Purchasing a laptop that matches the desired specifications for a particular specialization is tedious. The question in hand is “Do online reviews aid their decision-making for product (laptop) purchase?”. They all use different methods and approaches in order to form recommendations best suit their problem at hand. This study reviews the extant literature on product recommendation systems and proposes a Laptop Recommendation System based on a hybrid model, combining both Content-Based Filtering and Collaborative Filtering. The study captures data through the use of an online survey administered to undergraduate engineering respondents. The factors considered were processor, operating system, graphic card, and RAM (Random Access Memory). The data is analyzed through panda's library of python programming. The proposed specialization-based laptop recommendation system would be of benefit to engineering undergraduates to make an informed decision.