Scientists from MTUSI have developed an effective solution to estimate the demand for goods related to the relevant goods, especially in increasing sales conditions. The study examined machine learning methods to help the enterprise predict which goods to be requested. This greatly simplifies the task of analyzing large data sequences that traditional statistical methods cannot cope.
Machine learning models were used for the test, including XGboost, Lightgbm and others. Researchers Yuri Leokhin and Timur Fathulin evaluated them in three basic parameters: accuracy, stability and performance. Among the many tested solutions, the XGboost model, which combines the high accuracy and stability of the estimates, turned out to be the most effective. He worked with data from various sources, for example, retail chains and businesses, which made it universal.
The authors of the study stated that XGBOost was effective due to the probability of fine adjustments of the parameters. In the future, they plan to develop the model by paying more attention to selecting data processing and features. It may become the basis for creating smart forecasting systems that will find use in other fields where retail trade, production and product demand is important.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
