Automated Diagnosis and Cost Estimation for Smartphone Complaints

Abstract — Smartphones are a daily necessity but are frequently plagued by technical problems like battery drain, screen crack, charging problems, speaker faults, and software bugs Finding these problems is costly, time-consuming, and occasionally unreliable will leads to needless repairs and irate customers. In addition to automatically classify user-reported complaints into pre-established categories, this study proposes an intelligent automated system based on Natural Language Processing (NLP) and Machine Learning (ML). To improve diagnostic accuracy and efficacy, a Naïve Bayes classifier with TF-IDF vectorizer will analyzes text description to identify hardware or software issues. This automation system has a repair cost estimates function in addition to find and categorization, which provides users with estimated costs based on identified smartphone complaint issues by retrieving repair costs from service providers. To help users to make well-informed repair decisions, the price estimation model is updated frequently to reflect current market changes. This approach will helps to reduces manual diagnostic, increases customer happiness, and streamlines repair procedures by combining smartphone diagnostic problems with cost estimation. The technology gets very better over time through constant refinement, making it a very attractive and useful tool for the expanding smartphone repair industry.