This article aims to identify factors that influences income inequality and the method of multiple linear regression is used. The Gini coefficient is employed to measure the degree of income inequality, and multiple variables such as demographic trends, population health, and economic indicators are selected. Through regression analyses of data from China from 2001 to 2020 and data from 30 developed countries in 2020, it is found that in the Chinese model, multiple variables are closely related to the Gini coefficient, with a relatively high level of fitting. In the international model, only the net migration rate has a significant impact on the Gini coefficient, with a lower fitting than the Chinese model. This indicates that there are differences in the factors influencing income inequality between China and developed countries. What holds true for China may not be applicable to the international context, and vice versa. In the Chinese model, the combined effect of variables is more prominent, while in developed countries, the influences of other considered factors are likely to be more prominent.

The global crude oil market is influenced by geopolitical, supply-demand, and financial factors with important macroeconomic considerations. This research used a multivariate linear regression and an ARIMA time series model to explore past price behavior and forecast short-term trends. The primary variables involved are the macroeconomic variables, financial indicators, and measure of geopolitical risk. After addressing stationarity, this paper found the selected ARIMA model performed well and predicted generally decreasing oil prices one year ahead, with increasing confidence intervals around those predictions reflecting increasing uncertainty concerning future prices. Residual diagnostics support the adequacy of the model, but the model is constrained by structural breaks (e.g., financial crises, pandemic shocks) in data, and the omission of relevant exogenous variables. The results of the analysis reaffirm that the long-term price behavior of crude oil is driven by supply-demand fundamentals but highlight the pressure for hybrid models with machine learning algorithms that account for nonlinear relationships and structural breaks. The research provides actionable information for both policymakers and investors as they navigate volatile markets with important geopolitical risk factors.

Air pollution, a global environmental issue, is a growing concern in developing countries, particularly India. This study analyzes air quality data from 10 major districts of India from 2020-2024, focusing on the impact of seven pollutant indicators on the Air Quality Index (AQI). Data normalization was used to calculate AQI values based on international standards. Three linear regression models were constructed: a full parameter model, one focusing only on particulate matter (PM2.5, PM10), and one excluding other indicators. The experimental results show that the model with particulate matter as a predictor variable outperforms other models, confirming that PM2.5 and PM10 are key indicators for AQI prediction in Indian regions.

With the development of global economy and evolution of consumer concepts, automobiles, as an important means of transportation and consumer product, have seen a continuous increase in market demand. In recent years, with the growing number of vehicles in use, the second-hand car market has gradually become an important part of the automotive circulation sector. This study investigates the factors influencing second-hand car pricing in the current market environment. By combining multiple linear regression and Random Forest analysis, the author examines the significance and impact of various factors on the final selling price of second-hand vehicles. The data were collected from Kaggle and supplemented by relevant academic literature, covering variables such as power, transmission, mileage, engine type, and fuel type. The author seeks to reveal the characteristics and trends of current second-hand car pricing, provide guidance for marketing strategies, offer a basis for relevant policy-making, and explore the long-term impact of second-hand car pricing on the entire consumer market and social-economic development. As the results, the vehicle's power has the greatest impact on the final transaction price, which is the pricing in the second-hand car market, and it is positively correlated.

The communication network plays an increasingly important function in the Cyber-Physical Distribution System (CPDS) to ensure a dependable power supply as the quantity and type of terminal devices in power distribution systems increase.This article examines CPDS reliability in the context of wireless access conditions. We begin by developing a reliability model specifically for communication channels within a 5G network. Additionally, we introduce an enhanced evaluation method using an improved minimal path approach. Simulation results demonstrate that 5G communication technology significantly enhances system reliability, offering valuable insights for optimizing CPDS operations. Keywords: CPDS reliability, 5G communication network, wireless access, power distribution system,communication network reliability, improved minimal path method.

This study examines sustainable tourism in Juneau, Alaska, and Shanghai, addressing overtourism and environmental degradation. In 2023, Juneau received 1.6 million cruise tourists, generating $375 million but straining infrastructure and accelerating glacier retreat. To tackle these issues, a mathematical model is developed using ESG criteria, SDGs, and the GRI framework. The model incorporates tourist volume, revenue, and regulatory tools (e.g., caps, taxes), with objectives to minimize environmental impact, maximize social benefits, and enhance community satisfaction. Constraints such as emission limits and seasonal tourist thresholds ensure practical relevance. Time-series data are analyzed using Fourier series and linear regression. Multivariable dynamic programming determines optimal monthly tourist numbers. Sensitivity analysis highlights the dominance of environmental and governance factors, underscoring the role of government in sustaining local quality of life. A fuzzy optimization approach addresses real-world uncertainties. A revenue allocation plan channels funds to environmental protection (30%), water (20%), waste management (20%), infrastructure (15%), marketing (10%), and community projects (5%), aligning with sustainability goals.

Dynamic social networks present significant challenges for rapid identification of high-impact nodes, which is crucial for effective information dissemination in scenarios such as emergency management and enterprise marketing. This study introduces a hybrid optimization framework, MLE-GA, that integrates maximum likelihood estimation (MLE) with traditional genetic algorithms (GA) to address these challenges. In the proposed two-layer architecture, the outer GA layer performs a global search to optimize candidate seed node combinations, while the inner MLE layer dynamically estimates network parameters in real time, thereby constructing a probabilistic model that guides the evolution of the solution. Simulation experiments, including tests on synthetic datasets and real-world networks like Zachary’s Karate Club, demonstrate that MLE-GA achieves an error rate below 5% for identifying high-influence nodes, significantly outperforming conventional MLE approaches. The results confirm that the hybrid method not only effectively distinguishes between high- and low-influence nodes but also adapts to rapid changes in network structure, ensuring efficient resource allocation and robust optimization in dynamic environments. These findings underscore the potential of MLE-GA as a universal solution for complex social network problems where timely and accurate decision-making is imperative.

In this day and age, house-purchase has become a crucial consideration for almost everyone, whether seeking a residence or making an investment. Therefore, analyzing the relationship between these factors and house prices is vitally important for both buyers and sellers to make informed decisions. Some researchers have used a linear regression model that can predict the house price for a company or individual. This paper focuses on a target sample data set of “Houses in London” from Kaggle. The author firstly provides an analysis of two methods to model the relationship between the dependent variable, House Price, and an independent variable, Square Meters. These methods are the Simple Linear Regression Model (SLR) and Cubic Spline Interpolation polynomial (CSI), respectively. Then, a Hybrid House Price Prediction Model is established to predict the house price with specific Square Meters by integrating SLR and CSI. Finally, the author uses Multiple Linear Regression to model the effects of various independent variables from the target sample to the House Price. The research significance of this paper mainly includes increasing the accuracy and comprehensiveness of the House Prediction Model by constructing a Hybrid Model and using the MLR model, respectively.

Global warming has emerged as a critical global concern, with the control of greenhouse gas emissions becoming a paramount priority for nations worldwide. Carbon dioxide (CO₂), a significant greenhouse gas, comprises a substantial portion of vehicle exhaust emissions. To effectively mitigate CO₂ emissions from automobiles, it is imperative to identify and analyze the key determinants influencing these emissions. In this paper, the collected data were fitted into a model through multiple linear regression in R. The variance inflation factor (VIF) detection method was used to detect multicollinearity, and the stepwise regression method was employed to eliminate multicollinearity in the model to study the related factors of CO₂ emissions from automobiles. The findings indicate that engine size, number of cylinders, and combined fuel consumption are primary factors affecting CO₂ emissions from vehicles. Among them, the combined fuel consumption is the most significant influencing factor. These results offer valuable insights for automotive engineers and researchers, guiding efforts to enhance vehicle design and reduce CO₂ emissions.

As the car industry has been developed rapidly, the used car market has also shown its potential due to the affordability and ability to make prediction on prices. This study aims to predict the prices of used car by using two methods: Linear regression model and LightGBM model and make comparison on the performance of two models. The dataset used are found in Kaggle which contain 5847 groups of data with 11 different variables in total affecting the price. In this paper, only 10 variables are chosen to process in the two models and evaluate the results. It has been found that LightGBM model are better than linear regression model with a higher efficiency, suitability and accuracy, with an R2 value of 0.962 for the training set and 0.930 for the test set, compared to Linear Regression's R2value of 0.700. Additionally, LightGBM demonstrates lower prediction errors (MAE: 1.103, MSE: 4.858, RMSE: 2.204) and better handling of large-scale data. To conclude, the LightGBM model has higher accuracy and is more suitable to predict the used car prices with higher efficiency especially when processing complex, large-scale data compared to linear regression model.