International Journal of Science, Engineering and TechnologyAuthors: Mrs. K. Harika, Padala Sri Sai Harshitha, Cheekatla Sri Bindu Patvika, Sree Bala Damisetti, Palla Rambabu, Azhar Syed
Abstract: E-commerce start-ups are rapidly expanding in the digital economy, yet accurate estimation of initial investment and prediction of profitability remain critical challenges. This paper presents an enhanced data-driven framework that utilizes machine learning techniques to estimate start-up capital requirements and forecast future profitability. A structured dataset comprising key business indicators such as operational costs, marketing expenditure, infrastructure investment, and revenue-related factors is constructed and analysed. A regression-based predictive model is developed to identify relationships between these variables and financial outcomes. The proposed approach emphasizes effective data preprocessing, including normalization and outlier handling, to improve model reliability. Experimental evaluation demonstrates that the model is capable of extracting meaningful patterns and providing practical insights for financial planning. The results highlight the importance of feature influence in determining capital requirements and profit margins. This study contributes to the domain of intelligent business analytics by offering a scalable and interpretable solution that supports entrepreneurs and investors in making informed decisions. The integration of machine learning into financial forecasting enhances strategic planning and promotes sustainable growth in the competitive e-commerce landscape.
DOI:
