A multi-factor GDP nowcast model for India

Title: A multi-factor GDP nowcast model for India

Abstract: The post-pandemic period has underscored the need to improve nowcasting models for Indian GDP. This paper consolidates a diverse set of high-frequency economic indicators (HFIs) into multiple factors – nominal, survey-based, labor market, and real economic activity – to nowcast GDP growth. Unlike existing models that primarily focus on overall GDP nowcasts, we evaluate the contribution of each HFI by analyzing its impact on GDP nowcast revisions following new data releases. In addition, the COVID-19 pandemic introduced outliers in HFIs, distorting model parameters and reducing forecasting accuracy. To address this, we incorporate the Oxford Stringency Index and propose a novel data transformation based on sigmoid transformation that minimizes model sensitivity to large shocks. This approach enables the models to handle unexpected events more robustly without overreacting. Our methodology improves nowcasting models’ ability to handle outliers, providing valuable insights during volatile period.

Speaker Bio: Abhishek Ranjan is an Economist in the Strategic Research Unit at the Reserve Bank of India, Mumbai. He has previously worked at the Technical University of Denmark (Denmark), Shiv Nadar University (India), Université Paris 1 Panthéon-Sorbonne (France), and the University of California, Davis (USA). His research focuses on applied macroeconomics, econometrics, and machine learning, with applications in central banking, public sector consulting, and welfare economics. His work emphasizes statistical modeling, time series forecasting, and simulation.

Join Zoom Meeting
https://zoom.us/j/91980852910?pwd=m6G8GbanSeFUfUdCtYSVK2mbCi97T0.1

Meeting ID: 919 8085 2910
Passcode: 751199