Skip to content
Conference

Intelligent investment project evaluation system-based on ensemble learning and Bayesian optimization: multicriteria decision algorithm for investment decision efficiency

Sep 2026 · International Conference on Image Processing and Pattern Recognition · Vol 14388, pp. 143880O - 143880O-8 · 0 citations · 17 references
Engineering

Abstract

The pattern-based risk classification approach for the level of investment projects involves the following two major challenges: low discriminant efficiency and poor separability of features in high dimensional spaces. Traditional methods demonstrate significant computation barriers in dealing with large and heterogeneous project data sets, while their hyperparameters require manual tuning, limiting the development of effective discriminant boundaries in a dynamic environment. The suggested method involves the heterogeneous weak discriminant feature extractors using a Stacking methodology in which tree-based algorithms are responsible for capturing nonlinear local decision-making rules, while kernel-based algorithms develop global hyperplanes for discrimination. Furthermore, a novel multi-criteria adaptive acquisition function has been proposed for optimization of the discriminant feature space. The updating process of the Gaussian process posterior makes efficient exploration of the sample space possible. The cross-dataset generalization test and Pareto front analysis provide evidence on the stability of the algorithm in terms of the investment classification in diverse environments, while the t-SNE dimensionality reduction visualization suggests that the meta-feature space generated by the algorithm has better inter-class separability. The multi-objective performance decomposition and ablation tests validate the complementary effects of the discriminant modules. Overall, the algorithm provides a technical method of investment decision making by integrating both the accuracy of the classification and efficiency of optimization, which has significant practical significance.

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.