Traditional Linear Regression Research Articles

Predicting pharmaceutical prices. Advances based on purchase-level data and machine learning

BackgroundIncreased costs in the health sector have put considerable strain on the public budgets allocated to pharmaceutical purchases. Faced with such pressures amplified by financial crises and pandemics, national purchasing authorities are presented with a puzzle: how to procure pharmaceuticals of the highest quality for the lowest price. The literature explored a range of impactful factors using data on producer and reference prices, but largely foregone the use of data on individual purchases by diverse public buyers.MethodsLeveraging the availability of open data in public procurement from official government portals, the article examines the relationship between unit prices and a host of predictors that account for policies that can be amended nationally or locally. The study uses traditional linear regression (OLS) and a machine learning model, random forest, to identify the best models for predicting pharmaceutical unit prices. To explore the association between a wide variety of predictors and unit prices, the study relies on more than 200,000 purchases in more than 800 standardized pharmaceutical product categories from 10 countries and territories.ResultsThe results show significant price variation of standardized products between and within countries. Although both models present substantial potential for predicting unit prices, the random forest model, which can incorporate non-linear relationships, leads to higher explained variance (R2 = 0.85) and lower prediction error (RMSE = 0.81).ConclusionsThe results demonstrate the potential of i) tapping into large quantities of purchase-level data in the health care sector and ii) using machine learning models for explaining and predicting pharmaceutical prices. The explanatory models identify data-driven policy interventions for decision-makers seeking to improve value for money.

Nonlinear Relationship of Multi-Source Land Use Features with Temporal Travel Distances at Subway Station Level: Empirical Study from Xi’an City

The operation of the subway system necessitates a comprehensive understanding of passenger flow characteristics at station locations, as well as a keen awareness of the average travel distances at these stations. Moreover, the travel distances at the station level bear a direct relationship with the built environment composed of land use characteristics within the station’s catchment area. To this end, we selected the land use features within an 800 m radius of the station (land use area, distribution of points of interest, and the surrounding living environment) as the influencing factors, with the travel distances at peak hours on the subway network in Xi’an as the research subject. An improved SSA-XGBOOST-SHAP interpretable machine learning framework was established. The research findings demonstrate that the proposed enhanced model outperforms traditional machine learning or linear regression methods in terms of R-squared, MAE, and RMSE. Furthermore, the distance from the city center, road network density, the number of public transit routes, and the land use mix have a pronounced influence on travel distances, reflecting the significant impact that mature built environments can have on passenger attraction. Additionally, the analysis reveals a notable nonlinear relationship and threshold effect between the built environment variables comprising land use and the travel distances during peak hours. The research results provide data-driven support for operational strategy management and line capacity optimization, as well as theoretical underpinnings for enhancing the efficiency and sustainability of the entire subway system.

Nonlinear Relationship of Multi-Source Land Use Features with Temporal Travel Distances at Subway Station Level: Empirical Study from Xi’an City

The operation of the subway system necessitates a comprehensive understanding of passenger flow characteristics at station locations, as well as a keen awareness of the average travel distances at these stations. Moreover, the travel distances at the station level bear a direct relationship with the built environment composed of land use characteristics within the station’s catchment area. To this end, we selected the land use features within an 800 m radius of the station (land use area, distribution of points of interest, and the surrounding living environment) as the influencing factors, with the travel distances at peak hours on the subway network in Xi’an as the research subject. An improved SSA-XGBOOST-SHAP interpretable machine learning framework was established. The research findings demonstrate that the proposed enhanced model outperforms traditional machine learning or linear regression methods in terms of R-squared, MAE, and RMSE. Furthermore, the distance from the city center, road network density, the number of public transit routes, and the land use mix have a pronounced influence on travel distances, reflecting the significant impact that mature built environments can have on passenger attraction. Additionally, the analysis reveals a notable nonlinear relationship and threshold effect between the built environment variables comprising land use and the travel distances during peak hours. The research results provide data-driven support for operational strategy management and line capacity optimization, as well as theoretical underpinnings for enhancing the efficiency and sustainability of the entire subway system.

Adaptive Nighttime-Light-Based Building Stock Assessment Framework for Future Environmentally Sustainable Management

The accumulation of artificially built environment stock during urbanization processes has been actively involved in altering the material and energy use pattern of human societies. Therefore, an accurate assessment of built environment stock can provide insights for decision makers to implement appropriate environmentally sustainable retrofitting strategies. This study presents a building stock estimation enhancement framework (BSEEF) that leverages nighttime light (NTL) to accurately assess and spatially map building stocks. By innovatively integrating a region classification module with a hybrid region-specified self-optimization module, BSEEF adaptively enhances the estimation accuracy across diverse urban landscapes. A comparative case study of Japan demonstrated that BSEEF significantly outperformed a traditional linear regression model, with improvements ranging from 1.81% to 16.75% across different metrics used for assessment, providing more accurate building stock estimates. BSEEF enhances environment/sustainability studies by enabling precise spatial analysis of built environment stocks, offering a versatile and robust framework that adapts to technological changes and achieves superior accuracy without extensive reliance on complex datasets. These advances will make BSEEF an indispensable tool in strategic planning for urban development, promoting sustainable and resilient communities globally.

Adaptive Nighttime-Light-Based Building Stock Assessment Framework for Future Environmentally Sustainable Management

The accumulation of artificially built environment stock during urbanization processes has been actively involved in altering the material and energy use pattern of human societies. Therefore, an accurate assessment of built environment stock can provide insights for decision makers to implement appropriate environmentally sustainable retrofitting strategies. This study presents a building stock estimation enhancement framework (BSEEF) that leverages nighttime light (NTL) to accurately assess and spatially map building stocks. By innovatively integrating a region classification module with a hybrid region-specified self-optimization module, BSEEF adaptively enhances the estimation accuracy across diverse urban landscapes. A comparative case study of Japan demonstrated that BSEEF significantly outperformed a traditional linear regression model, with improvements ranging from 1.81% to 16.75% across different metrics used for assessment, providing more accurate building stock estimates. BSEEF enhances environment/sustainability studies by enabling precise spatial analysis of built environment stocks, offering a versatile and robust framework that adapts to technological changes and achieves superior accuracy without extensive reliance on complex datasets. These advances will make BSEEF an indispensable tool in strategic planning for urban development, promoting sustainable and resilient communities globally.

Uptake of zinc from the soil to the wheat grain: Nonlinear process prediction based on artificial neural network and geochemical data

Trace elements in plants primarily derive from soils, subsequently influencing human health through the food chain. Therefore, it is essential to understand the relationship of trace elements between plants and soils. Since trace elements from soils absorbed by plants is a nonlinear process, traditional multiple linear regression (MLR) models failed to provide accurate predictions. Zinc (Zn) was chosen as the objective element in this case. Using soil geochemical data, artificial neural networks (ANN) were utilized to develop predictive models that accurately estimated Zn content within wheat grains. A total of 4036 topsoil samples and 73 paired rhizosphere soil-wheat samples were collected for the simulation study. Through Pearson correlation analysis, the total content of elements (TCEs) of Fe, Mn, Zn, and P, as well as the available content of elements (ACEs) of B, Mo, N, and Fe, were significantly correlated with the Zn bioaccumulation factor (BAF). Upon comparison, ANN models outperformed MLR models in terms of prediction accuracy. Notably, the predictive performance using ACEs as input factors was better than that using TCEs. To improve the accuracy, a two-step model was established through multiple testing. Firstly, ACEs in the soil were predicted using TCEs and properties of the rhizosphere soil as input factors. Secondly, the Zn BAF in grains was predicted using ACE as input factors. Consequently, the content of Zn in wheat grains corresponding to 4036 topsoil samples was predicted. Results showed that 85.69 % of the land was suitable for cultivating Zn-rich wheat. This finding offers a more accurate method to predict the uptake of trace elements from soils to grains, which helps to warn about abnormal levels in grains and prevent potential health risks.

Confounding amplifies the effect of environmental factors on COVID-19

The global COVID-19 pandemic has severely impacted human health and socioeconomic development, posing an enormous public health challenge. Extensive research has been conducted into the relationship between environmental factors and the transmission of COVID-19. However, numerous factors influence the development of pandemic outbreaks, and the presence of confounding effects on the mechanism of action complicates the assessment of the role of environmental factors in the spread of COVID-19. Direct estimation of the role of environmental factors without removing the confounding effects will be biased. To overcome this critical problem, we developed a Double Machine Learning (DML) causal model to estimate the debiased causal effects of the influencing factors in the COVID-19 outbreaks in Chinese cities. Comparative experiments revealed that the traditional multiple linear regression model overestimated the impact of environmental factors. Environmental factors are not the dominant cause of widespread outbreaks in China in 2022. In addition, by further analyzing the causal effects of environmental factors, it was verified that there is significant heterogeneity in the role of environmental factors. The causal effect of environmental factors on COVID-19 changes with the regional environment. It is therefore recommended that when exploring the mechanisms by which environmental factors influence the spread of epidemics, confounding factors must be handled carefully in order to obtain clean quantitative results. This study offers a more precise representation of the impact of environmental factors on the spread of the COVID-19 pandemic, as well as a framework for more accurately quantifying the factors influencing the outbreak.

Spatial non-stationarity test of regression relationships in the multiscale geographically weighted regression model

By allowing covariate-specific bandwidths for estimating spatially varying coefficients, the multiscale geographically weighted regression (MGWR) model can simultaneously explore spatial non-stationarity and multiple operational scales of the corresponding geographical processes. Treating the constant coefficients as an extreme situation which corresponds to the global scale and infinite covariate bandwidth, the traditional linear regression, GWR and mixed GWR models are special cases of the MGWR model. An appropriately-specified GWR-based model would be beneficial to the understanding of the general underlying processes, especially for their operational scales. To specify an appropriate model, the key issue is to determine how many MGWR coefficient(s) should be constant. Along the traditional statistical line of thought, we propose a residual-based bootstrap method to test spatial non-stationarity of the MGWR coefficients, which can underpin our understanding of the characteristics of regression relationships in statistics. The simulation experiment validates the proposed test, and demonstrates that it is of valid Type I error and satisfactory power, and is robust to different types of model error distributions. The applicability of the proposed test is demonstrated in a real-world case study on the Shanghai housing prices.

Anomalous Warm Temperatures Recorded using Tree Rings in the Headwater of the Jinsha River during the Little Ice Age

As a feature of global warming, climate change has been a severe issue in the 21st century. A more comprehensive reconstruction is necessary in the climate assessment process, considering the heterogeneity of climate change scenarios across various meteorological elements and seasons. To better comprehend the change in minimum temperature in winter in the Jinsha River Basin (China), we built a standard tree-ring chronology from Picea likiangensis var. balfouri and reconstructed the regional mean minimum temperature of the winter half-years from 1606 to 2016. This reconstruction provides a comprehensive overview of the changes in winter temperature over multiple centuries. During the last 411 years, the regional climate has undergone seven warm periods and six cold periods. The reconstructed temperature sensitively captures the climate warming that emerged at the end of the 20th century. Surprisingly, during 1650–1750, the lowest winter temperature within the research area was about 0.44 °C higher than that in the 20th century, which differs significantly from the concept of the “cooler” Little Ice Age during this period. This result is validated by the temperature results reconstructed from other tree-ring data from nearby areas, confirming the credibility of the reconstruction. The Ensemble Empirical Mode Decomposition method (EEMD) was adopted to decompose the reconstructed sequence into oscillations of different frequency domains. The decomposition results indicate that the temperature variations in this region exhibit significant periodic changes with quasi-3a, quasi-7a, 15.5-16.8a, 29.4-32.9a, and quasi-82a cycles. Factors like El Niño–Southern Oscillation (ENSO), Pacific Decadal Oscillation (PDO), and solar activity, along with Atlantic Multidecadal Oscillation (AMO), may be important driving forces. To reconstruct this climate, this study integrates the results of three machine learning algorithms and traditional linear regression methods. This novel reconstruction method can provide valuable insights for related research endeavors. Furthermore, other global climate change scenarios can be explored through additional proxy reconstructions.

Subway track foundation settlement deformation prediction based on the BiLSTM-AdaBoost model

The rapid economic expansion has spurred extensive construction near subway networks, impacting the stability of their track foundations. Consequently, it’s crucial to monitor and predict settlement in subway track foundations. However, the dynamic deformation patterns often exhibit nonlinearity and non-stationarity, posing challenges for traditional linear regression models. To tackle this, our study integrates the BiLSTM (bi-directional long short-term memory) network with the AdaBoost ensemble learning algorithm. Using settlement data from Shanghai metro monitoring points, the model is trained and evaluated employing R2 (coefficient of determination), MAE (mean absolute error), and RMSE (root mean square error). Results show that our proposed model displays superior predictive accuracy compared to the LSTM and the BiLSTM, with an average training set R2 of 0.99, test set R2 of 0.78, average MAE of 0.32 mm, and average RMSE of 0.4 mm. Consequently, for forecasting subway track foundation deformations, employing our network model ensures highly accurate predictive capabilities.

Machine learning-based comparison of factors influencing estimated glomerular filtration rate in Chinese women with or without non-alcoholic fatty liver.

The prevalence of non-alcoholic fatty liver (NAFLD) has increased recently. Subjects with NAFLD are known to have higher chance for renal function impairment. Many past studies used traditional multiple linear regression (MLR) to identify risk factors for decreased estimated glomerular filtration rate (eGFR). However, medical research is increasingly relying on emerging machine learning (Mach-L) methods. The present study enrolled healthy women to identify factors affecting eGFR in subjects with and without NAFLD (NAFLD+, NAFLD-) and to rank their importance. To uses three different Mach-L methods to identify key impact factors for eGFR in healthy women with and without NAFLD. A total of 65535 healthy female study participants were enrolled from the Taiwan MJ cohort, accounting for 32 independent variables including demographic, biochemistry and lifestyle parameters (independent variables), while eGFR was used as the dependent variable. Aside from MLR, three Mach-L methods were applied, including stochastic gradient boosting, eXtreme gradient boosting and elastic net. Errors of estimation were used to define method accuracy, where smaller degree of error indicated better model performance. Income, albumin, eGFR, High density lipoprotein-Cholesterol, phosphorus, forced expiratory volume in one second (FEV1), and sleep time were all lower in the NAFLD+ group, while other factors were all significantly higher except for smoking area. Mach-L had lower estimation errors, thus outperforming MLR. In Model 1, age, uric acid (UA), FEV1, plasma calcium level (Ca), plasma albumin level (Alb) and T-bilirubin were the most important factors in the NAFLD+ group, as opposed to age, UA, FEV1, Alb, lactic dehydrogenase (LDH) and Ca for the NAFLD- group. Given the importance percentage was much higher than the 2nd important factor, we built Model 2 by removing age. The eGFR were lower in the NAFLD+ group compared to the NAFLD- group, with age being was the most important impact factor in both groups of healthy Chinese women, followed by LDH, UA, FEV1 and Alb. However, for the NAFLD- group, TSH and SBP were the 5th and 6th most important factors, as opposed to Ca and BF in the NAFLD+ group.

Private Firm Valuation Using Multiples: Can Artificial Intelligence Algorithms Learn Better Peer Groups?

Forming optimal peer groups is a crucial step in multiplier valuation. Among others, the traditional regression methodology requires the definition of the optimal set of peer selection criteria and the optimal size of the peer group a priori. Since there exists no universally applicable set of closed and complementary rules on selection criteria due to the complexity and the diverse nature of firms, this research exclusively examines unlisted companies, rendering direct comparisons with existing studies impractical. To address this, we developed a bespoke benchmark model through rigorous regression analysis. Our aim was to juxtapose its outcomes with our unique approach, enriching the understanding of unlisted company transaction dynamics. To stretch the performance of the linear regression method to the maximum, various datasets on selection criteria (full as well as F- and NCA-optimized) were employed. Using a sample of over 20,000 private firm transactions, model performance was evaluated employing multiplier prediction error measures (emphasizing bias and accuracy) as well as prediction superiority directly. Emphasizing five enterprise and equity value multiples, the results allow for the overall conclusion that the self-organizing map algorithm outperforms the traditional linear regression model in both minimizing the valuation error as measured by the multiplier prediction error measures as well as in direct prediction superiority. Consequently, the machine learning methodology offers a promising way to improve peer selection in private firm multiplier valuation.

Application of Machine Learning Models in Asset Allocation

This study embarks on an exploration of machine learning (ML) models in forecasting the trends of stock indices, with a specific focus on different industries within the Chinese market. Moving beyond the confines of traditional linear regression and standard multi-factor approaches, our research adopts a multi-dimensional analytical framework to decode the complex relationships between various factors and the future returns of industry-specific Exchange-Traded Funds (ETFs) in China. The paper innovatively applies both linear and nonlinear ML models to predict directional shifts in ETF returns, a domain not extensively studied previously. We conduct a thorough comparative analysis of these models, assessing their predictive prowess and dissecting the influence of diverse factors on different industry sectors. This investigation reveals distinct patterns and factor sensitivities unique to each sector, offering new insights into their dynamics. The results are pivotal for asset allocation and investment strategies, as they highlight the nuanced role of ML in financial forecasting. By bridging the gap between traditional financial models and advanced ML techniques, our study presents a novel perspective that enriches the strategic planning in financial markets, especially in the context of the rapidly evolving Chinese economy.

Development of an artificial neural network based-prediction model for bond strength of FRP bars in concrete

Fiber-reinforced polymer (FRP) bars have garnered increasing attention in recent years due to their superior corrosion resistance, offering a potential solution to the significant drawback of steel corrosion in concrete. For the widespread utilization of FRP bars in concrete structures, determining the bond strength between FRP bars and concrete is a crucial topic. This study seeks to develop a prediction model to estimate the bond strength of FRP bars in concrete, utilizing an extended dataset from 1010 pull-out tests. Initially, the study evaluates the applicability of several bond strength formulas from existing codes. Subsequently, two prediction models, namely a multivariate linear regression model and an artificial neural network (ANN) model, are introduced for estimating the bond strength of FRP bars in concrete. The results indicate that the correlation between the evaluation values of existing formulas and the experimental value is very low. This is because these formulas have not yet been updated to encompass the expanded usage scopes of FRP bars with various surface processing methods and types of concrete. While the multivariate linear regression model outperforms these formulas, its accuracy is still relatively low; in contrast, the ANN demonstrates superior performance, achieving an R^2 value for both the validation and test set of more than 0.92. The findings highlight that, when considering a broader range of applications, the ANN serves as a robust tool for accurately predicting the bond strength of FRP bars in concrete, in comparison to traditional formulas and linear regression models. This assessment approach provides engineers with a convenient, high-precision tool for designs utilizing various forms of FRP bars and diverse types of concrete in practical design scenarios

Predicting the fire-induced structural performance of steel tube columns filled with SFRC-enhanced concrete: using artificial neural networks approach

Predicting the axial Shortening strength of concrete-filled steel tubular (CFST) columns is an important problem that this study attempts to solve for civil engineering projects. We suggest using a deep learning-based artificial neural network (ANN) model to address this issue, taking into account the intricate relationship between steel tube and core concrete. The model, called ANN-SFRC (Steel Fibre Reinforced Concrete), surpasses an R2 threshold of 0.90 and achieves impressive R2 values across different types of CFST columns. Compared to traditional linear regression methods, the ANN-SFRC model significantly improves accuracy, with an observed inaccuracy of less than 3% compared to actual values. With its reliable approach to forecasting the behavior of CFST columns under axial compression, this high-performance instrument enhances safety and accuracy during the design and planning stages of civil engineering.

Machine Learning Prediction of Prediabetes in a Young Male Chinese Cohort with 5.8-Year Follow-Up.

The identification of risk factors for future prediabetes in young men remains largely unexamined. This study enrolled 6247 young ethnic Chinese men with normal fasting plasma glucose at the baseline (FPGbase), and used machine learning (Mach-L) methods to predict prediabetes after 5.8 years. The study seeks to achieve the following: 1. Evaluate whether Mach-L outperformed traditional multiple linear regression (MLR). 2. Identify the most important risk factors. The baseline data included demographic, biochemistry, and lifestyle information. Two models were built, where Model 1 included all variables and Model 2 excluded FPGbase, since it had the most profound effect on prediction. Random forest, stochastic gradient boosting, eXtreme gradient boosting, and elastic net were used, and the model performance was compared using different error metrics. All the Mach-L errors were smaller than those for MLR, thus Mach-L provided the most accurate results. In descending order of importance, the key factors for Model 1 were FPGbase, body fat (BF), creatinine (Cr), thyroid stimulating hormone (TSH), WBC, and age, while those for Model 2 were BF, white blood cell, age, TSH, TG, and LDL-C. We concluded that FPGbase was the most important factor to predict future prediabetes. However, after removing FPGbase, WBC, TSH, BF, HDL-C, and age were the key factors after 5.8 years.

Machine learning prediction of hospitalization costs for coronary artery bypass grafting operations

BackgroundWith the steady rise in health care expenditures, the examination of factors that may influence the costs of care has garnered much attention. Although machine learning models have previously been applied in health economics, their application within cardiac surgery remains limited. We evaluated several machine learning algorithms to model hospitalization costs for coronary artery bypass grafting. MethodsAll adult hospitalizations for isolated coronary artery bypass grafting were identified in the 2016 to 2020 Nationwide Readmissions Database. Machine learning models were trained to predict expenditures and compared with traditional linear regression. Given the significance of postoperative length of stay, we additionally developed models excluding postoperative length of stay to uncover other drivers of costs. To facilitate comparison, machine learning classification models were also trained to predict patients in the highest decile of costs. Significant factors associated with high cost were identified using SHapley Additive exPlanations beeswarm plots. ResultsAmong 444,740 hospitalizations included for analysis, the median cost of hospitalization in coronary artery bypass grafting patients was $43,103. eXtreme Gradient Boosting most accurately predicted hospitalization costs, with R2 = 0.519 over the validation set. The top predictive features in the eXtreme Gradient Boosting model included elective procedure status, prolonged mechanical ventilation, new-onset respiratory failure or myocardial infarction, and postoperative length of stay. After removing postoperative length of stay, eXtreme Gradient Boosting remained the most accurate model (R2 = 0.38). Prolonged ventilation, respiratory failure, and elective status remained important predictive parameters. ConclusionMachine learning models appear to accurately model total hospitalization costs for coronary artery bypass grafting. Future work is warranted to uncover other drivers of costs and improve the value of care in cardiac surgery.

Advances in warfarin's anticoagulation therapy in Chinese population after mechanical valve replacement

Warfarin is an irreplaceable oral anticoagulant for patients with mechanical heart valves, the stable pharmacogenetic-based warfarin dose prediction algorithms have improved the effectiveness and safety of warfarin anticoagulation therapy. Genetic factors are the main factors affecting the stable dose of warfarin. Single nucleotide polymorphisms such as VKORC1 and CYP2C9 affect the anticoagulation effect of warfarin through pharmacodynamic or pharmacokinetic pathways. Age, body surface area, combined use of drugs, and other nongenetic factors also affect the stable dose of warfarin. Previously published algorithms for warfarin dose prediction included mainly the white race, and most algorithms were constructed using traditional multiple linear regression. However, domestic studies have used machine learning methods to construct warfarin dose prediction algorithms based on the Chinese Han post-mechanical valve replacement population and have achieved better prediction efficiency. This article reviews the advances of warfarin anticoagulation influencing factors and the clinical application of stable dose prediction algorithms.

The Construction of Economic Education Model Based on the Spatial Durbin Model

This research attempts to address the complexities and the nuances that are a part of the economic education by proposing an innovative model that is grounded in the Spatial Durbin Model (SDM). The spatial interdependencies which are crucial for the understanding of the regional variations in the economic implications and the efficacy of the educational policies are sometimes neglected by the conventional main frames of the economic education. The integration of the SDM, which is a sophisticated spatial econometric tool, aims to offer a thorough and detailed understanding of the intricate relationships between the education and the economic development in context of the diverse geographics. The model that is proposed in this research study extends beyond the traditional linear regressions as it accounts for the spatial autocorrelation and the spatial lag effects which thereby captures the spatial spillover and the diffusion of the educational investments and policies. With the help of the empirical analysis which moves forward by the utilization of the spatial econometric techniques such as the spatial lag and the spatial error models, strives to explore the spatial dynamics of the economic education while identifying the spatial patterns, the dependencies involved and the disparities that come up in the attainment of the educational and the economic performance. By incorporation of the spatial dimensions into the economic education model, the policymakers and the educators are able to get their hands on the in depth insights. This is into the spatially differentiated impacts of the educational interventions which tends to enable a more targeted and a more effective design and implementation of the policy. Furthermore, the proposed model also aims to facilitate the identification of the spatially targeted strategies in order to address the regional disparities with respect to the educational outcomes and the economic growth. Hence, it contributes to a more inclusive and a sustainable development trajectory. Through the interdisciplinary effort of bridging the economics, education and the spatial analysis, this research extends a valuable main frame for the policymakers, educators and the researchers which helps in attaining better understanding and helps to address the multifaceted challenges as well as the opportunities in the economic education and the regional development. Ultimately, this has enhanced the understanding of the spatial dimensions of the economic education which leads to the evidence based policies and interventions which are aimed at nurturing the equitable and resilient economic growth. In this paper, we utilize the spatial Durbin model as a framework to investigate the role that advanced degrees play in driving technological innovation in various parts of the world. Spatial self-correlation and instability in the geographic distribution of post-graduates in China were shown by data from the regional panel in China between 2004 and 2018. Advanced degrees facilitated the advancement of cutting-edge technologies.

Going a Step Deeper Down the Rabbit Hole: Deep Learning Model to Measure the Size of the Unregistered Economy Activity

AbstractAccurately estimating the size of unregistered economies is crucial for informed policymaking and economic analysis. However, many studies seem to overfit partial data as these use simple linear regression models. Recent studies adopted a more advanced approach, using non-linear models obtained using machine learning techniques. In this study, we take a step forward on the road of data-driven models for the unregistered economy activity’s (UEA) size prediction using a novel deep-learning approach. The proposed two-phase deep learning model combines an AutoEncoder for feature representation and a Long Short-Term Memory (LSTM) for time-series prediction. We show it outperforms traditional linear regression models and current state-of-the-art machine learning-based models, offering a more accurate and reliable estimation. Moreover, we show that the proposed model is better in generalizing UEA’s dynamics across countries and timeframes, providing policymakers with a more profound group to design socio-economic policies to tackle UEA.