This paper aims to explore the stability of input-output (I-O) coefficients, a critical aspect of economic modeling that reflects the interdependencies between industries in an economy. Despite the widespread use of I-O models in economic analysis, the stability of these coefficients over time remains a contentious issue, raising concerns about the reliability of economic forecasts derived from them. This study restates key issues surrounding I-O coefficient stability, including factors influencing their variability, the impact of structural changes in the economy, and methodological approaches for assessing stability. By synthesizing existing literature and empirical findings, we highlight the importance of understanding the conditions under which I-O coefficients may fluctuate and their implications for economic policy and planning. The paper concludes with recommendations for future research aimed at improving the robustness and accuracy of I-O models, ultimately contributing to more effective economic decision-making.

This study examines the application of machine learning algorithms to enhance financial inclusion in microfinance, focusing on credit scoring, risk and fraud detection, and customer segmentation. We performed feature engineering and employed models such as Logistic Regression, Decision Trees, Random Forests, Gradient Boosting Machines (XGBoost and LightGBM), Support Vector Machines (SVM), Autoencoders, Isolation Forests, and K-means Clustering. LightGBM achieved the highest accuracy (89.6%) and AUC (0.92) in credit scoring, while Random Forests demonstrated strong performance in both loan approval (86.7% accuracy) and fraud detection (87.6% accuracy, AUC of 0.88). SVM also performed competitively, and unsupervised methods like Autoencoders and Isolation Forests showed potential for anomaly detection but required further refinement.K-means Clustering excelled in customer segmentation with a silhouette score of 0.72, enabling tailored services based on client demographics. Our findings highlight the significant impact of machine learning on improving credit scoring accuracy, reducing fraud risks, and enhancing customer service delivery in microfinance, thereby promoting financial inclusion for underserved populations. Ethical considerations and model interpretability are crucial, particularly for smaller institutions. This study advocates for the broader adoption of machine learning in the microfinance sector.

ZENODO DOI:- https://doi.org/10.5281/zenodo.14044729

Small businesses often face challenges in leveraging data-driven strategies due to resource constraints, limiting their ability to optimize operations, forecast finances, and retain customers effectively. This study presents a machine learning framework designed to support small business management by focusing on key areas: customer retention, financial forecasting, customer segmentation, and inventory management. Utilizing real-world small business data, we evaluate various machine learning models, including Random Forest, Gradient Boosting, K-Means Clustering, Lasso Regression, and ARIMA, to determine the optimal algorithms for each business function. Our findings reveal that Random Forest excels in customer retention, Lasso Regression performs well in financial forecasting, K-Means effectively segments customers, and ARIMA accurately predicts inventory requirements. By integrating these models into a cohesive framework, small businesses can gain actionable insights without the need for extensive computational resources. This framework thus enables small businesses to implement cost-effective, ethical, and interpretable machine learning solutions, empowering them to compete more effectively in data-driven markets. This research contributes to the growing field of AI in small business, providing a practical approach for deploying machine learning models that meet the specific needs of small enterprises.