An exploratory data analysis approach for analyzing financial accounting data using machine learning

Abstract

Analyzing financial accounting transactions is essential for gaining valuable hidden insights, optimizing performance, reducing expenses by identifying more efficient methods of conducting business operations, and improving profitability and bottom line. This study uses exploratory data analysis to analyze financial accounting data, including balance sheets, income statements, and cash flow statement data. Such descriptive analytics considers various parameters, such as the Debt-to-Equity Ratio, Current Ratio, Return on Capital Employed, Net Profit Margin, and Inventory Turnover Ratio, to determine profitability for investment decisions. Afterward, predictive analytics is used to predict total revenue as a dependent variable. Four supervised machine learning models are employed: Linear Regression, K-Nearest Neighbor, Support Vector Regressor, and Decision Tree. The results suggest that the decision tree is the most valuable model for performance analytics. The hyperparameter is the maximum depth of the tree, and its optimal value of nine is determined using a grid search.