Online Sales Prediction in E-Commerce Market Using Machine Learning

• Published in: 2023 4th International Conference on Signal Processing and Communication (ICSPC) pp. 47 - 51
• Main Authors: Ajaykrishna, S., Suganya, T.S., Rao, Beema, Pughazendi, N.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 23-03-2023
• DOI: 10.1109/ICSPC57692.2023.10125855

Product sales anticipation assumes a key part in upgrading idealness of item conveyance in E-Commerce. Among numerous heterogeneous provisions pertinent to sales estimating, advancement crusades held in E-Commerce and contending connection amid substitutable items would significantly muddle the substance. Unlikely, these variables are typically neglected in the current research; since the regular time-series investigation-based procedures principally believe the business records unaided. In this article, we make use of the previous data in online trade market to build up the framework to anticipate sales. As stated by the qualities of diverse data, 3-sorts of expectation techniques are: Incentive-Auto-Regressive-Integrated-Moving-Average (I-ARIMA), Long-Short-Term-Memory (LSTM) and Artificial-Neural-Network (ANN). These 3-techniques can handle the concern with diverse exactness necessities and various data types. Broad investigations are led more than two genuine datasets in diverse areas from E-Commerce. Outcomes reveal that the LSTM gets munificent implementation attain over others and modern intense learning choices as far as anticipating precision. This research considers the benefits and inconveniences of the three kinds of strategies on diverse informational repositories and gives considerable rules to traders on their advertising methodologies.