Forecasting is a very important task not only for any business but also in other fields. There are numerous categories to forecast in business, but determining the future revenue (revenue forecast) is one of most crucial task so that leader can propose appropriate policies, decisions to optimize production and business activities. Revenue forecasting is a complex problem and requires the use of many different methods and techniques to achieve the highest accuracy. This study mainly analyzes approaches to select neural network models, processes, highlights the necessary steps and leverages advancements in deep learning for revenue forecast on a set of revenue data generated in the monthly, quarterly period from 2013 to June 2019 of 9 regions in Tra Vinh province. The considered telecommunication services groups including Internet services, MyTV service, landline phone service and postpaid mobile service are taken into account for revenue forecast tasks with the deep learning techniques. The proposed method achieves promising results and is already deployed in the practical cases at VNPT Tra Vinh.
Tạp chí khoa học Trường Đại học Cần Thơ
Lầu 4, Nhà Điều Hành, Khu II, đường 3/2, P. Xuân Khánh, Q. Ninh Kiều, TP. Cần Thơ
Điện thoại: (0292) 3 872 157; Email: tapchidhct@ctu.edu.vn
Chương trình chạy tốt nhất trên trình duyệt IE 9+ & FF 16+, độ phân giải màn hình 1024x768 trở lên