APPLICATION OF STATISTICAL TECHNIQUES IN RAILWAY DATA ANALYSIS

The integration of statistical techniques into railway operations has become a critical driver of efficiency, reliability, and competitiveness in modern transportation systems. This article examines how Azerbaijan Railways applies three core statistical methods—regression, clustering, and forecasting—to optimize performance and support data-driven decision-making. Regression analysis is widely used to quantify relationships among key operational factors. For instance, regression models predict train delays based on weather conditions and seasonal passenger fluctuations, while also providing insights into revenue forecasting from ticket sales. Clustering techniques are applied to segment both passenger and freight data, enabling Azerbaijan Railways to group customers by travel behaviour, such as frequent commuters or tourists, and to classify freight according to weight, volume, and destination. These applications enhance targeted marketing, loyalty program design, and freight logistics efficiency. Forecasting plays a pivotal role in strategic and operational planning, with time series models predicting passenger demand, freight volumes, and equipment maintenance cycles. Such forecasts allow the company to proactively allocate capacity during peak seasons, schedule staff more effectively, and implement predictive maintenance to minimize equipment failures and service disruptions. Collectively, these statistical approaches not only improve current operational efficiency but also strengthen Azerbaijan Railways’ ability to adapt to future challenges. By embedding regression, clustering, and forecasting into its digital transformation strategy, the company enhances customer satisfaction, optimizes resources, and maintains resilience in an increasingly competitive transport sector. Keywords: Azerbaijan Railways, Statistical Techniques, Regression Analysis, Clustering, Forecasting.