Abstract
In contemporary sales management, organizations face persistent challenges in efficiently navigating the sales funnel to convert leads into customers. Despite technological advancements and evolving sales methodologies, optimizing each stage of the sales funnel remains a challenging task. The emergence artificial intelligence (AI)-driven predictive analytics offers a promising avenue to enhance sales performance. However, the precise impact of integrating AI-driven predictive analytics into sales strategies is still uncertain, necessitating focused research to evaluate its effectiveness and potential for improving sales outcomes.
This study aims to assess the effective utilization of prediction models in optimizing organizational systems (Material Requirements Planning and Inventorty management), evaluate the accuracy of seasonal sales forecasts generated by these models in the mining equipment sales industry. Archived sales data was extracted from the company data storage Enterprise Resource Planning (ERP) software used to manage various business processes, including the sales of units. It is capable of storing and processing data across departments, integrating operations like finance, supply chain, manufacturing, and customer relationship management (CRM), then processed and analyzed using Python. Five time series Holt-Winters, Prophet, Extreme Gradient Boosting (XGBoost), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Recurrent Neural Network (RNN)—were compared to determine the most accurate model for predicting sales. The accuracy of Holt-Winters, SARIMA, Prophet, XGBoost, and RNN models was found to be 86.73%, 85.15%, 77.31%, 87.75%, and 88.34%, respectively.
The results of the study demonstrated that the RNN model was the most accurate predictive model for mining equipment sales, achieving an accuracy of 88.34% and it was used to predict the sales for the next 6 months. The prediction was used to show how MRP can be optimized in reducing lead time from twelve weeks to one week and optimizing inventory management by keeping safety stock to boost CRM and ultimately leading to increased sales.