Data Analysis Approach to Predict Revenue using Financial Statement.

Accurate revenue prediction plays a vital role in strategic financial planning, yet many existing systems rely on rigid, traditional statistical methods that fail to effectively capture complex patterns within financial statement data. These systems often lack the flexibility to handle non-linear relationships and multivariate financial indicators, leading to suboptimal forecasting. This research introduces a modern, data-driven solution by applying Exploratory Data Analysis (EDA) to uncover hidden trends and outliers in financial datasets. Subsequently, two machine learning models—Linear Regression and K-Nearest Neighbor (KNN)—are implemented and compared to evaluate their performance in predicting revenue. The proposed system aims to improve accuracy, adaptability, and practical usefulness in real-world financial decision-making scenarios.