Abstract :

India Is The World’s Second-largest Smartphone Market, With Over 750 Million Users And Annual Shipments Exceeding 150 Million Units. Rapid Growth In 4G/5G Adoption, Affordable Data, And Digital Services Has Intensified Competition Among Brands. Consumers Now Evaluate Phones Based On Price, Performance, Battery, Camera, And Connectivity Features. The Objective Is To Analyze Smartphone Specifications To Predict Price And Performance Trends Accurately, Helping Consumers Make Informed Choices And Assisting Manufacturers In Competitive Product Positioning. In A Manual System, Smartphone Evaluation Is Done Through Human Comparison Of Specifications, Expert Reviews, Price Listings, And Personal Judgment. Buyers Or Analysts Read Product Descriptions, Compare Features Across Brands, Check Ratings, And Decide Value-for-money Based On Experience And Intuition Rather Than Data-driven Insights. Manual Comparison Is Time-consuming, Subjective, And Prone To Bias. It Cannot Efficiently Handle Large Datasets Or Capture Complex Relationships Between Features And Price. Accuracy Depends Heavily On Human Expertise, Leading To Inconsistent Decisions, Limited Scalability, And Difficulty In Adapting To Rapidly Changing Market Trends. The Motivation Is To Overcome Manual Limitations By Improving Accuracy, Scalability, And Objectivity. The Proposed System Employs Machine Learning Models Such As Decision Tree (DT), Support Vector Regression (SVR), And Gradient Boosting (GB) To Predict Smartphone Price And Performance Based On Specifications. DT Provides Interpretable Rule-based Decisions, Helping Understand Feature Importance. SVR Effectively Models Complex, Non-linear Relationships Between Hardware Attributes And Price. GB Combines Multiple Weak Learners To Achieve High Predictive Accuracy And Robustness. Together, These Models Automate Analysis, Improve Prediction Precision, Handle Largescale Data Efficiently, And Significantly Outperform Manual Evaluation Methods In Consistency And Reliability.

Published:

27-3-2026

Issue:

Vol. 26 No. 3 (2026)

Page Nos:

760-768

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite