Should I Buy It? A Smart Guide for Consumers.

Abstract

The objective of this project is to develop a mechanism that can automatically respond to a consumer’s query regarding the purchase of a product based on the feedback provided by experts and other consumers available on the website. This report explores different techniques used for smart guidance for consumers. Different stages involving Classification, Relevance ranking, and opinion mining will be studied and discussed. This project uses Natural Language Processing (NLP), Pattern Recognition (PR), and Machine Learning (ML) techniques to develop the model. Through these techniques, it is feasible to design an automated system that can compile and summarize relevant feedbacks to generate the most relevant response to a consumer’s query. Such a system can facilitate Convenience and guidance. This model first classifies the query entered by the customer as either open-ended or binary, then summarizes feedbacks of reviewers into their relevant parts and ranks reviews by relevance to apply a voting-based model to generate a relevant response Opinion mining is applied to find keywords in reviews relevant to user queries to differentiate facts from subjective opinions. Recommendations for future development and conclusions are also included in the report. The outcome of the project can add value to existing e-commerce practices and improve customer experience.