Effective Demand Forecasting Model Using Business Intelligence Empowered With Machine Learning

• Main Authors: Muhammad Adnan Khan, Shazia Saqib, Tahir Alyas, Anees Ur Rehman, Yousaf Saeed, Asim Zeb, Mahdi Zareei, Ehab Mahmoud Mohamed
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Business intelligence; demand forecasting; prediction; machine learning; AWS sage maker; sale forecasting
• Online Access: https://ieeexplore.ieee.org/document/9121220/

In the modern era business intelligence (BI) has a pivotal role in articulating a strategy and taking correct measures based on data. Business intelligence plays a pivotal role in an inevitable decision support system that enables the enterprise to perform analysis on data and throughout the process of business. Machine learning predicts the forecasting of future demands of the enterprises. Demand forecasting is one of the main decision-making tasks of enterprise. For demand forecasting first raw sales data is collected from the market, then according to data, the future sale/product demands are forecasted. This prediction is based on collected data that compiles through different sources. The machine learning engine executes data from different modules and determines the weekly, monthly, and quarterly demands of goods/commodities. In demand forecasting, its perfect accuracy is non-compromising, the more accurate system model is more efficient. Furthermore, we test the efficiency by comparing the predicted data with actual data and determine the percentage error. Simulation results show that after applying the purposed solution on real-time organization data, we get up to 92.38 % accuracies for the store in terms of intelligent demand forecasting.