A Framework for Predictive Futuristic Trend and Demand Analysis for Reengineering the Fashion Industry

Abstract

This thesis proposes an intelligent forecasting system for the online retail of fashion articles. The empirical study utilizes data from an online fashion retailer, comprising articles information, customer information, and corresponding transactions between them to enhance future demand prediction. The proposed forecasting model leverages machine learning and deep learning techniques to be applied to the merged dataset with features necessary for the prediction of sales. Python language is used for executing the research work. Efficient preprocessing techniques like label encoding and normalizing are applied to improve the accuracy of the model. By employing supervised machine learning regression algorithms and artificial intelligence algorithms on labeled data, the aim is to select the best-fit model based on performance metrics. After comparing the results of RMSE score metrics with other algorithms, the algorithm giving the better result is chosen as the model for prediction. Conclusively the best-fit model is further deployed to be integrated into a web-based application using Flask- a micro-framework for Python. The web application works on the dataset with the help of a model finalized for predicting sales and trends of fashion articles. newlineThe results demonstrate the promising performance of the proposed forecast model on the tested items, suggesting its effective utilization in solving forecasting challenges within the fashion industry. newline newline