Predicting Smartphone And Laptop Market Success With Machine Learning
predicting, product success, technology market, smartphones, laptops, machine learning techniques, data collection process, predictive model, threshold-based feature analysis, user-friendly web applications.
This thesis presents a novel approach to predicting product success in the technology market, with a specific focus on smartphones and laptops. Leveraging machine learning techniques and a meticulous data collection process, the study develops a predictive model that can serve as a tool for manufacturers, marketers, and decision-makers in the technology industry. The research employs a threshold-based feature analysis methodology to classify product success. This approach integrates domain knowledge and customer preferences, resulting in clear and interpretable criteria for success. Feature engineering’s importance is underscored, particularly in the creation of ‘average rating’ and ‘percentage success’ metrics.
The data collection process, encompassing product specification selection, is meticulously detailed. The robustness of this process ensures a comprehensive and relevant dataset for both smartphones and laptops, forming a solid foundation for the subsequent predictive modeling. The development, training, and evaluation of Random Forest Classifier models form the heart of the thesis. Their performance on test data is thoroughly analyzed and visualized , examining metrics such as accuracy, precision, recall, F1 score, and ROC AUC. The implications of these results are discussed in depth, offering insights into the predictive power and limitations of the models.
The versatility of the threshold-based feature analysis method is demonstrated through its application to laptops and phones. The process of adapting the method to different product categories is discussed, highlighting its broad applicability. A key feature of the study is the deployment of the predictive models using Streamlit, an open-source app framework. This interactive web application allows users to input specific product features and receive a prediction for product success, making the outcomes of this research practically applicable and user-friendly.
Inconclusion, this thesis contributes a valuable predictive model for product success
in the technology market. It offers a comprehensive exploration of the process, results, and implications of using machine learning techniques for predicting product success, and its deployment in a user-friendly web application. The study opens avenues for future research in this area, potentially extending the methodology to other product categories and incorporating more complex machine learning techniques.
"Predicting Smartphone And Laptop Market Success With Machine Learning", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.9, Issue 10, page no.c840-c849, October-2024, Available :https://ijnrd.org/papers/IJNRD2410300.pdf
Volume 9
Issue 10,
October-2024
Pages : c840-c849
Paper Reg. ID: IJNRD_301563
Published Paper Id: IJNRD2410300
Downloads: 00025
Research Area: Science and Technology
Country: Visakhapatnam, Andhra Pradesh, India
ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJNRD (IJ Publication) Janvi Wave
