Optimization of energy usage decisions through predictive modeling of consumption patterns

By constructing a correlation network between global sea surface temperature anomalies (SSTAs) and summer precipitation anomalies in the Yunnan–Guizhou Plateau, key SST regions influencing summer precipitation anomalies in the Yunnan–Guizhou Plateau were selected. It was found that spring SSTAs in the Bay of Bengal, southwestern Atlantic, and eastern Pacific are crucial for influencing summer precipitation anomalies in the Yunnan–Guizhou Plateau. Setting SSTAs from these three regions as predictor variables 3 months in advance, we constructed multiple linear regression (MLR), ridge regression (RR), and lasso regression (LR) models to predict summer precipitation anomalies over the Yunnan–Guizhou region. The training phase involved data spanning from 1961 to 2005, which aimed to predict precipitation anomalies in the Yunnan–Guizhou Plateau for the period extending from 2006 to 2022. Based on MLR, RR, and LR models, the correlations between predicted values and observed summer precipitation anomalies in Yunnan–Guizhou were 0.48, 0.46, and 0.46, respectively. These values were all higher than the correlation coefficients of the NCC_CSM model’s predicted and observed values. Additionally, its performance in predicting summer precipitation anomalies over the Yunnan–Guizhou region, based on key SST regions, was assessed using performance metrics such as anomaly correlation coefficient (ACC), anomaly sign consistency rate (PC), and trend anomaly comprehensive score (PS score). The average ACC of MLR, RR, and LR models was higher than that of the NCC_CSM model’s predictions. For MLR, RR, LR, and NCC_CSM models, the PCs exceeding 50% of the year were 14, 14, 11, and 10, respectively. Furthermore, the average PS score for predicting summer precipitation anomalies over the Yunnan–Guizhou region using MLR, RR, and LR was approximately 73 points; 8 higher than the average PS score of the NCC_CSM model. Therefore, predicting summer precipitation anomalies over the Yunnan–Guizhou region based on key SST regions is of great significance for improving the prediction skills of precipitation anomalies in this region.

An accurate energy consumption prediction becomes crucial with increasing electric vehicle usage for effective power grid management. This research examined the performance of eleven machine learning models for this purpose: Ridge Regression, Lasso Regression, K-Nearest Neighbors, Gradient Boosting, Support Vector Regression, Multi-Layer Perceptron, XGBoost, CatBoost, LightGBM, Gaussian Processes for Regression(GPR) and Extra Trees Regressor, considering real historical data from Colorado. The models were evaluated using different metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), R², Root Mean Squared Error(RMSE) and Normalized Root Mean Squared Error(NRMSE), with visual analyses through scatter plots and time series plots. The best model observed was the Extra Trees Regressor, which had an MAE of 0.5888, an MSE of 3.2683, R² value of 0.9592, RMSE of 1.8078 and NRMSE of 0.020. Gradient Boosting and KNN also returned good results, although they were slightly more dispersed. Nevertheless, while non-linear models like MLP, XGBoost, CatBoost, LightGBM and linear models such as Ridge and Lasso Regression offer valuable insights, they exhibit shortcomings in estimating energy, especially at extreme levels, highlighting limitations in capturing complex non-linear interactions. This study focuses on their applicability to energy projections to demonstrate how well ensemble and non-linear models may capture intricate patterns in time series. These cutting-edge machine learning techniques might greatly enhance energy demand predictions.

Based on the fiscal revenue and other relevant economic index data of Beijing from 1995 to 2020, this study uses the research methods of Ridge regression and Lasso regression to explore the influencing factors of Beijing’s fiscal revenue. Considering that the traditional linear regression model will produce strong multicollinearity among many variables. Therefore, ridge regression and Lasso regression model were firstly used to reduce the influence of multicollinearity between variables, and then variable selection was carried out. Finally, the two models were compared according to the analysis results, and the optimal analysis model was selected. The results show that compared with ridge regression model, lasso regression model has better goodness of fit, smaller error and better model. The added value of the second industry, power generation, resident population, urban per capita disposable income and total retail sales of social consumer goods has a positive impact on fiscal revenue, and the whole social fixed assets investment, employment in cities and towns, per capita consumption expenditure of urban households is has a certain negative impact on fiscal income level.

As the secondary housing market continues to play a vital role in the global real estate industry, there is an increasing demand for accurate and efficient prediction of secondary housing prices. In this study, transaction data from the second-hand housing market in Ames, Iowa, USA, available on the Kaggle website, was utilized. A total of 79 influential feature variables, including Lot Area, Overall Quality, and Year Built, were selected to construct seven different models for predicting secondary housing prices: Linear Regression, Lasso Regression, Ridge Regression, LassoCV, RidgeCV, Random Forest, and Neural Network models. To assess the effectiveness of these models, we utilized a range of evaluation metrics including the R2 score, Mean Absolute Error (MAE), and Mean Squared Error (MSE). The results indicated that the RidgeCV model stood out among the others, displaying the most robust predictive performance with a goodness-of-fit of 90.3%. This discovery holds significant implications for improving the accuracy of secondary housing valuation.

Under-5 mortality remains a critical social indicator of a country's development and economic sustainability, particularly in developing nations like Bangladesh. This study employs machine learning models, including Linear Regression, Ridge Regression, Lasso Regression, Bayesian Ridge, Decision Tree, Gradient Boosting, XGBoost, and CatBoost, to forecast future trends in under-5 mortality. By leveraging these models, the study aims to provide actionable insights for policymakers and health professionals to address persistent challenges. Data from the 1993-94 to 2017-18 Bangladesh Demographic and Health Survey (BDHS) was analyzed using advanced machine learning algorithms. Key metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), R-squared, and Mean Absolute Percentage Error (MAPE), were employed to evaluate model performance. Additionally, k-fold cross-validation was conducted to ensure robust model evaluation. This study confirms a significant decline in under-5 mortality in Bangladesh over the study period, with machine learning models providing accurate predictions of future trends. Among the models, Linear Regression emerged as the most accurate, achieving the lowest MAE (4.05), RMSE (4.56), and MAPE (6.64%), along with the highest R-squared value (0.98). Projections indicate further reductions in under-5 mortality to 29.87 per 1,000 live births by 2030 and 26.21 by 2035. From 1994 to 2018, under-5 mortality in Bangladesh decreased by 76.72%. While the Linear Regression model demonstrated exceptional accuracy in forecasting trends, long-term predictions should be interpreted cautiously due to inherent uncertainties in socio-economic conditions. The forecasted rates fall short of the Sustainable Development Goal (SDG) target of 25 deaths per 1,000 live births by 2030, underscoring the need for intensified interventions in healthcare access and maternal health to achieve this target.

Multicollinearity arises when two or more regressors are correlated in multiple linear regression model (MLRM) and in most cases, one regressor variable can be predicted from another. Multicollinearity majorly results in inefficient regression model estimates and poor performance of the regression model. However, multicollinearity problem can easily be handled using various methods such as ridge regression, lasso regression, principal components regression, etc. This study compared the effectiveness of two estimators in handling multicollinearity problem in a given dataset. The estimators being compared are ridge estimator (RE) and principal components estimator (PCE). This research uses secondary data obtained from World Bank database, International Monetary Fund (IMF) database, and the Nigerian Debt Management Office to compare the two approaches of handling multicollinearity problem in MLRM. The presence of multicollinearity in the dataset was established using the correlation matrix of predictors and the Variance Inflation Factors (VIF's). Then ridge regression and principal components regression methods were used to fit models to the dataset respectively and their mean squared errors (MSE) were obtained. The MSE was used as performance evaluation measure for the regression models. Both methods addressed the problem multicollinearity in the datasets but the ridge estimator performed better than PCE by having the smallest mean squared error.

Soil swelling is the most destructive geo-hazard recorded in history, considering its influence on the durability and stability of structures. The purpose of this study is to predict the one-dimensional swelling potential of soil through the Least Absolute Shrinkage and Selection Operator (LASSO) regression, Ridge regression, and Multiple Linear Regression (MLR). The database of soils extracted from literature was obtained by means of predictive laboratory experiments, including plasticity index (Ip), dry density (γd), plastic limit (PL), liquid limit (LL), and clay. The novelty of this study lies in the utilization of Lasso and Ridge regression models in soil swell potential prediction. The model’s performance metrics were mean absolute percentage error (MAPE), mean deviation (MD), root mean square error (RMSE), and coefficient of determination (R2). The results demonstrate that Lasso outperformed the other techniques with a performance accuracy of R2 values of 0.872, 0.746, 0.935, 0.931 at RMSE values of 0.106%, 0.167%, 0.046%, 0.051%. The results of this work have practical implications for engineers and advance soil mechanics when addressing swelling potential areas and machine learning applications in geotechnical engineering, to overcome the rampant laboratory visitation in search of soil data needed for slope stability, ground improvement, earthworks, and seismic analysis. Specifically, when dealing with swell potential areas, the study’s predictive assistance in making better-informed decisions regarding the construction and design phases.

The analyzed study focuses on the application of predictive models, specifically Linear Regression and Decision Trees, for the management of delinquent debts in the public context of the United States. The main objective of the work is to compare the effectiveness of these models in predicting the compliance of debts older than 120 days, helping to direct these debts to the Treasury Offset Program (TOP), an essential initiative for government financial recovery. The problem that the study addresses is the need for effective management of delinquent public debts, seeking to ensure compliance with public financial policies that promote compliance and the proper redirection of financial resources to the government. This is particularly important to ensure fiscal transparency and accountability of federal agencies. The methodology used in the study was quantitative, based on the analysis of eligible debt data extracted from U.S. Treasury reports. The Linear Regression and Decision Trees models were applied, with performance metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Coefficient of Determination (R²). The study dealt with financial and temporal variables to analyze the behavior of these debts and their compliance. The main results show that both models showed high accuracy in the predictions, with the Linear Regression showing a perfect fit (R² = 1) and the Decision Trees excelling in capturing nonlinear nuances of the data. The "Compliance Rate Amount" variable was identified as the most significant in the Decision Tree model, suggesting that the amount of the compliance rate is one of the most important factors to predict the compliance of delinquent debts. This study offers valuable contributions to the field of public management, by demonstrating that the use of predictive models can help optimize debt recovery, improve fiscal transparency, and contribute to more informed decision-making.

The rising popularity and increasing financial acceptance of cryptocurrency are having a profound impact on global scale. Unlike the current fiat currencies, bitcoins offer a unique possibility to predict their price. Despite the fact that many individuals are investing in cryptocurrencies, little is known about their dynamic properties and predictability, which puts money at risk. The aim of this paper is to evaluate and compare different regression algorithms in order to forecast the price of most popular cryptocurrency – Bitcons. Secondary bitcoin historical data from Kaggle which features an updated daily record of 24 variables over a seven-year period ARE considered. Since the bitcoin data is so volatile, we implemented an effective pre-processing of data in order to have a better prediction result. The different models applied include – Linear Regression, Ridge Regression, LASSO Regression and Elastic Net Regression model. However, elastic net performed better with an RMSE of 0.0228 without showing signs of overfitting.

Since multi-omics data (high-dimensional data, including many variables, like genomics, transcriptomics and proteomics) are high-dimensional (have many variables), heterogeneous (are data of different types), and interdependent (variables can affect each other), there is a significant challenge in integrating various data types in a synergistic manner (without, it may not be feasible). This paper is an attempt to tackle the problem of predicting drug sensitivity by offering a hybrid machine learning (ML, algorithms that learn patterns by analyzing data) and deep learning (DL, a type of ML based on neural network architectures to learn patterns of data) model of not only predicting drug sensitivity, but also using Genomics of Drug Sensitivity in Cancer (GDSC) data. The method involves applying sophisticated preprocessing, strict feature selection techniques (Random Forest, tree-based algorithm; LASSO regression, feature selection that chooses features by pruning irrelevant ones; Mutual Information which is a dependency measure between variables) as well as a hybrid model design favoring classical ML models (Random Forest, SVM--Support Vector Machine) over the deep learning style (LSTM-Long short-term memory networks, a sequence-based version of recurrent neural network). The metrics of the evaluation give a very high R 2 (coefficient of determination, a measure of model fit) of 0.991, and the evaluations are very small MAE ( Mean absolute error: square root of average squared error), RMSE (Root mean squared error: square root of average squared error), and MSE ( Mean squared error: square root of average squared error), resulting in approximately 12 percent higher accuracy than conventional approximations: Ridge Regression, XGBoost (Extreme gradient boosting), and Random Forest alone. This also shows the strength (capacity to work with diverse circumstances), generalizability (capacity to be used in new information), and enhanced predictive capabilities of the hybrid method of modeling nonlinear associations in multi-omics information, thus enhancing precision medicine (health care customized to patients in terms of genetic, environmental, and lifestyle determinants) uses.

Accurate forecasting of economic indicators is essential for informed policy-making and strategic financial planning. This study presents a comprehensive comparative statistical analysis of multiple machine learning regression models—including linear regression, ridge regression, lasso regression, support vector regression, and random forest regression—for predicting key economic indicators such as GDP growth, unemployment rate, and inflation. Using a simulated dataset of 1000 samples with multiple economic features, each model’s performance was evaluated using mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination ($R^2$). Results indicate that ensemble methods such as random forest provide superior predictive accuracy, while regularized models outperform ordinary linear regression. Visualizations of predicted versus actual values, residual analyses, and statistical comparisons are provided to support the findings. Implications for model selection and economic forecasting are discussed.

Malaria is among the leading causes of mortality and morbidity among children in Ghana. Therefore, identifying the predictors of malaria prevalence in children under-five is among the priorities of the global health agenda. In Ghana, the paradigm shifts from using traditional statistics to machine learning techniques to identifying predictors of malaria prevalence are scarce. Thus, the present study used machine learning techniques to identify variables to build the best fitting predictive model of malaria prevalence in Ghana. We analysed the data on 2867 under-five children with malaria RDT results from the 2019 Ghana Malaria Indicator Survey. LASSO, Ridge, and Elastic Net regression methods were used to select variables to build predictive models. The R freeware version 4.0.2 was used. One out of four children tested positive for malaria (25.04%). The logit models based on selected features by LASSO, Ridge, and Elastic Net contained eleven, fifteen, and thirteen features, respectively. The LASSO regression model is preferred because it contains the smallest number of predictors and the smallest prediction error. The significant predictors of malaria among children were being older than 24months, residing in the poorest household, being severely anaemic, residing in households without electricity, and residing in a rural area. The predictors identified in our study deserve policy attention and interventions to strengthen malaria control efforts in Ghana. The machine learning techniques employed in our study, especially the LASSO regression technique could be beneficial for identifying predictors of malaria prevalence in this group of children.

Abstract. Recent studies have investigated the use of satellite imaging combined with machine learning for modelling the Chlorophyll-a (Chl-a) concentration of bodies of water. However, most of these studies use satellite data that lack the temporal resolution needed to monitor dynamic changes in Chl-a in productive lakes like Laguna Lake. Thus, the aim of this paper is to present the methodology for modelling the Chl-a concentration of Laguna Lake in the Philippines using satellite imaging and machine learning algorithms. The methodology uses images from the Himawari-8 satellite, which have a spatial resolution of 0.5–2 km and are taken every 10 minutes. These are converted into a GeoTIFF format, where differences in spatial resolution are resolved. Additionally, radiometric correction, resampling, and filtering of the Himawari-8 bands to exclude cloud-contaminated pixels are performed. Subsequently, various regression and gradient boosting machine learning algorithms are applied onto the train dataset and evaluated, namely: Simple Linear Regression, Ridge Regression, Lasso Regression, and Light Gradient Boosting Model (LightGBM). The results of this study show that it is indeed possible to integrate algorithms in Machine Learning in modelling the near real-time variations in Chl-a content in a body of water, specifically in the case of Laguna Lake, to an acceptable margin of error. Specifically, the regression models performed similarly with a train RMSE of 1.44 and test RMSE of 2.51 for Simple Linear Regression and 2.48 for Ridge and Lasso Regression. The linear regression models exhibited a larger degree of overfitting than the LightGBM model, which had a 2.18 train RMSE.

Augmented regression models using neurochaos learning

Forecasting Foreign Exchange Rate Movements with k-Nearest-Neighbour, Ridge Regression and Feed-Forward Neural Networks