Corporate financing decisions, particularly the choice between equity and debt, significantly impact a company’s financial health and value. This study predicts binary corporate debt levels (high or low) using supervised machine learning (ML) models and firms’ characteristics as predictive variables. Key features include companies’ size, tangibility, profitability, liquidity, growth opportunities, risk, and industry. Deterministic models, represented by logistic regression and multilevel logistic regression, and stochastic approaches that incorporate a certain degree of randomness or probability, including decision trees, random forests, Gradient Boosting, Support Vector Machines, and Artificial Neural Networks, were evaluated using usual metrics. The results indicate that decision trees, random forest, and XGBoost excelled in the training phase but showed higher overfitting when evaluated in the test sample. Deterministic models, in contrast, were less prone to overfitting. Notably, all models delivered statistically similar results in the test sample, emphasizing the need to balance performance, simplicity, and interpretability. These findings provide actionable insights for managers to benchmark their company’s debt level and improve financing strategies. Furthermore, this study contributes to ML applications in corporate finance by comparing deterministic and stochastic models in predicting capital structure, offering a robust tool to enhance managerial decision-making and optimize financial strategies.

Carefully selecting variables in problems with large volumes of data are extremely important, as it reduces the complexity of the model, improves the interpretation of the results, and increases computational efficiency, ensuring more accurate and relevant analyses. This paper presents a comprehensive approach to selecting variables in multiple regression models using the stepwise procedure. As the main contribution of this study, we present the stepwise function implemented in Python to improve the effectiveness of statistical analyses, allowing the intuitive and efficient selection of statistically significant variables. The application of the function is exemplified in a real case study of real estate pricing, validating its effectiveness in improving the fit of regression models. In addition, we presented a methodological framework for treating joint problems in data analysis, such as heteroskedasticity, multicollinearity, and nonadherence of residues to normality. This framework offers a robust computational implementation to mitigate such issues. This study aims to advance the understanding and application of statistical methods in Python, providing valuable tools for researchers, students, and professionals from various areas.

This article provides an overview of count data and count models, explores zero inflation, introduces likelihood ratio tests, and explains how the Vuong test can be used as a model selection criterion for assessing overdispersion. The motivation of this work was to create a Vuong test implementation from scratch using the Python programming language. This implementation supports our objective of enhancing the accessibility and applicability of the Vuong test in real-world scenarios, providing a valuable contribution to the academic community, since Python did not have an implementation of this statistical test.

This paper evaluates a physical model for estimating the energy consumption of Battery Electric Vehicles (BEVs) in urban deliveries, as well as proposing an analysis of the impact of speed, road profile, load weight, and number of stops on the range of these vehicles. The proposed microscopic physical model is based on vehicle dynamics equations, considering exponential battery regeneration during braking events. Physical parameters and auxiliary system consumption of the BEV are taken from the literature, and a standard driving cycle is proposed, with a speed and acceleration profile based on real-world data. A total of 160 distinct scenarios were simulated, varying the vehicle’s maximum speed, road profile, load weight and number of stops. The results demonstrate that these factors have a significant and quantifiable effect on BEV range. Uphill road grades can reduce range by up to 63% compared to flat terrain, while higher speeds substantially increase energy consumption – range is up to 88% higher at 10 km/h and 54% lower at 80 km/h, compared to a baseline of 40 km/h.

This research aims to evaluate the impact of vehicle components, driving conditions, and environmental factors on the energy consumption calculations along route segments in solutions for the Capacitated Electric Vehicle Routing Problem (EVRPC) in last-mile deliveries. A mathematical model was proposed for the problem, and solutions were obtained using the Gurobi solver. The energy consumption estimation model accounts for driver behavior (including speed, acceleration, and braking), topography, vehicle load, auxiliary system usage, and the operation of the regenerative braking system. To enhance the accuracy of predictions, the energy consumption calculation was further refined using a machine learning model trained with real-world consumption data. This study seeks to address the gap in integrated methodologies for estimating energy consumption within routing models for Battery Electric Vehicles (BEVs) in last-mile deliveries. The results demonstrate that the proposed mathematical model significantly optimizes the average utilization of BEVs compared to a baseline scenario, reducing the fleet size required to meet demand. The optimized routes result in lower total distance traveled and reduced overall energy consumption, with less variability in consumption. These findings suggest that more sophisticated methodologies can enhance the reliability of predictions and improve delivery operations. Furthermore, incorporating vehicle dynamics and using a nonlinear energy consumption estimate greatly influences the routing problem's results. Replacing a single linear parameter with a variable consumption model — considering factors such as speed, acceleration, braking, topography, load, auxiliary system usage, and temperature — enables more efficient delivery strategies, better battery conservation, and reduced State of Health (SOH) loss.

Count data analysis presents unique challenges due to its discrete nature, often exhibiting excessive zeros and overdispersion. To address these complexities, count models, such as Poisson regression and Negative Binomial regression, have been developed, enabling modeling and prediction of count-based phenomena. Additionally, it’s important to notice that zero inflation, a phenomenon commonly observed in count data, requires specialized techniques for robust analysis. This article provides an overview of count data and count models, explores zero inflation, introduces Likelihood Ratio Tests, and explains how the Vuong Test can be used as a model selection criteria. Furthermore, we created a Vuong Test implementation from scratch using the Python programming language. This implementation enhances the accessibility and applicability of the Vuong Test in real-world scenarios, providing a valuable contribution to the academic community, since Python didn’t have an implementation of this statistical test.