Efficient Hyper-Parameter Tuning for the Kappa Regression Algorithm
Publication Date: 2024/12/11
Summary: Kappa Regression algorithm has been shown to provide great performance results, but hyper-parameter tuning can, at times, be computationally intensive. The algorithm in-cludes a single parameter for each feature and a global parameter is required when features are combined. We have found, experimentally, that the prediction error is a convex function of the parameter value.
View Paper
Kappa Encoding Using the Huber Loss Function
Publication Date: 2024/11/4
Summary: Kappa Regression algorithm is a previously proposed method with excellent performance but requires significant computational effort for parameter tuning. In the Feature Encoding process the distance, for a given feature, between two samples is computed in terms of a common unit, namely that of the tagged value. We can determine the Huber Loss parameter value that optimizes the overall performance.
View Paper
Improving National Competitiveness Through the Optimized Allocation of Governmental Resources
Publication Date: 2024/11/4
Summary: We investigate the impact of ICT adoption, skills of the workforce, and Research and Development (R&D) expenditure on a country's overall competitiveness score. We used various regression models to analyse the relationships between these variables and competitiveness. The results also indicate that reducing mobile broadband service prices significantly improved I CT adoption.
View Paper
Predicting Event Participation for an Event-Based Social Network
Publication Date: 2024/11/4
Summary: Study examines user engagement within the Venzi event-based social networking app. Key factors influencing attendance and turnout rate-the percentage of approved users who attend-are identified and used to build predictive models. The analysis highlights the significance of user interaction metrics in forecasting event outcomes.
View Paper
On the Prediction of a Multidimensional Vulnerability Index for Climate Resilience
Publication Date: 2024/11/4
Summary: Study proposes an innovative application of machine learning modeling techniques to forecast the Multidimensional Vulnerability Index scores for climate-vulnerable countries. This paper presents the first comprehensive attempt to apply machine learning to vulnerability prediction on the international scale. It offers a data-driven approach to guide policy decisions in disaster.
View Paper