Cost-sensitive regression learning on small dataset through intra-cluster product favoured feature selection

Abstract

Massive regression and forecasting tasks are generally cost-sensitive regression learning problems with asymmetric costs between overprediction and under-prediction. However, existing classic methods, such as clustering and feature selection, are subject to difficulties in dealing with small datasets. As one of the key challenges, it is difficult to statistically validate the importance of features using traditional algorithms (e.g. the Boruta algorithm) owing to insufficient available data. By leveraging the feature information intra-cluster (item group with similar attributes), we propose an intra-cluster product favoured (ICPF) feature selection algorithm to select the information based on the traditional filtering method (specifically the Boruta algorithm in our study). The experimental results show that the ICPF algorithm significantly reduces the number of dimensions of the selected feature set and improves the performance of cost-sensitive regression learning. The misprediction cost decreased by 33.5% (linear-linear cost function) and 32.4% (quadratic-quadratic cost function) after adopting the ICPF algorithm. In addition, the advantage of the ICPF algorithm is robust to other regression models, such as random forest and XGboost.

Backorder Prediction in Inventory Management: Classification Techniques and Cost Considerations

“…Moreover, these studies contribute to forecasting by integrating backorders into traditional inventory models and enhancing our understanding of managing backorders in inventory management. In a different approach, researchers combined ARIMA and ANN for backorder prediction ( [11], [12]). The development of a Bayesian method for demand forecasting based on compound Poisson distributions is a significant contribution that outperforms other current methods [13].…”

“…By restricting the number of features considered at each split, the base estimators are forced to make more independent decisions, which can lead to a more robust The BBC combines the advantages of bagging and sampling techniques to address the issue of imbalanced datasets [20]. Several researchers in recent times and the past have recommended fuzzy logic (e.g., [11], [20], [21], [22], [23], [24], [25]). The objective is to add human-centric design along with advanced machine-learning algorithms.…”