A research team at Washington State University has created a forecasting model to help businesses more accurately predict customer demand, even when vital data is missing. The new method promises to significantly optimize operations and improve decision-making across multiple industries.
Researchers at Washington State University (WSU) have unveiled an innovative forecasting model designed to help businesses more accurately predict customer demand, even in the absence of complete data. This breakthrough, published in the journal Production and Operations Management, has the potential to transform how companies in various industries make critical operational and strategic decisions.
Developed by Xinchang Wang, an assistant professor of operations management at WSU’s Carson College of Business, and Weikun Xu, a doctoral student in management science at the same institution, the new model uses a mathematical approach to forecast customer interest with unprecedented accuracy.
“Most businesses can only see part of the demand picture — they know who buys but not how many people considered buying and didn’t,” Wang said in a news release. “Our model reconstructs the missing pieces, giving companies a more complete and reliable demand estimate.”
Traditional forecasting methods often rely on broad assumptions, such as market share estimates, which can lead to inaccuracies in understanding customer behavior and missed revenue opportunities.
In contrast, Wang and Xu’s model estimates both sales and the total number of potential customers, even accounting for those who considered but ultimately decided against making a purchase.
Using a computational technique known as the sequential minorization-maximization algorithm, the researchers were able to improve demand forecasting accuracy. This method eliminates the uncertainties that plague conventional forecasting by pinpointing the most reliable demand prediction from multiple possibilities.
“By eliminating uncertainty, businesses can make more confident pricing decisions,” Wang added.
While the researchers tested their model with airline ticket sales data, its design ensures applicability across various industries, according to Wang. For example, hotels could use it to predict future bookings, retail stores to estimate market demand and e-commerce platforms to understand shopping cart abandonment rates.
“This model provides a powerful tool for industries where incomplete data has been a persistent challenge,” added Wang. “By improving demand forecasting, businesses can plan more effectively, optimize operations and ultimately become more competitive.”
The implications of this research are far-reaching. Accurate demand forecasting can lead to better inventory management, optimized pricing strategies and enhanced customer satisfaction, ultimately giving businesses a significant competitive edge.
Source: Washington State University