KALYANKUMAR S

Price estimation in railway tenders. We will prepare railway tender price quotation on behalf of (railway’s private firms) using machine learning models and analysis to estimate the cost of a major item; we determine the cost of the major item by considering the effect of the prices of the raw materials used in it.

Parametric analysis of railway infrastructure for improved performance and lower life-cycle costs using machine learning techniques and quantifying the impact of monetary and fiscal policies to financial credit markets by railways. Lead model development with SQL database creation, data query automation, imputation, normalization, Unstructured and missing data cleaning and analyses the data using SQL, Python Libraries and other tools, preprocessing (using PCA and PCR) and optimization to support usage for railways and multiple goods releases. Drive implementation of scalable machine learning models, such as neural networks and clustering, with large time series datasets, composed of thousands of macroeconomic indicators, to deal with non-linear relationships that were impractical by the regression-based time series models and algorithm models. Research on evaluation metrics, variable selections, and cross-validation visualization dashboard. Research findings have been adopted by multiple teams across the railway. In charge of an A/B test (experiment design and result analysis) leading to ₹ 9,206 Cr incremental annual revenue.