• J Saran Prakash
• Dr. Swati sah

Sales prediction is a critical task for businesses, as it helps them make informed decisions regarding inventory management, resource allocation, and financial planning. With the rise of big data analytics and machine learning, businesses now have access to powerful tools to predict sales with greater accuracy. This study aims to compare traditional and modern approaches for sales prediction using big data analytics and machine learning. The traditional approach involves using statistical methods and time-series analysis to predict sales, while the modern approach involves using machine learning algorithms such as decision trees, random forests, and neural networks. In this study, we analyze the performance of both approaches on a dataset of sales transactions from a retail store. We compare the accuracy, speed, and scalability of the two approaches and evaluate the potential benefits and drawbacks of each approach. Our results show that the modern approach outperforms the traditional approach in terms of accuracy, with machine learning algorithms achieving significantly higher predictive accuracy than traditional statistical methods. Additionally, the modern approach is more scalable and faster than the traditional approach, enabling businesses to analyze larger datasets and make faster predictions. However, the modern approach requires more computational resources and may be more complex to implement than the traditional approach.

Sales prediction, Machine Learning Technique, Big Data Analytics.

"Big Data Analytics and Machine Learning for Sales Prediction: A Comparative Study of Traditional and Modern Approaches", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.g179-g182, March-2023, Available :http://www.jetir.org/papers/JETIR2303627.pdf

"Big Data Analytics and Machine Learning for Sales Prediction: A Comparative Study of Traditional and Modern Approaches", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. ppg179-g182, March-2023, Available at : http://www.jetir.org/papers/JETIR2303627.pdf