# Exploring predictive models to improve the accuracy of Housing Price Index forecasts in India’s real estate sector

## TL;DR

This study improves housing price forecasts in India using a new model with digital payment and economic data.

## Contribution

The study introduces the U-MIDAS model with novel predictors for forecasting India's Housing Price Index.

## Key findings

- HPI and digital payments are positively correlated.
- The U-MIDAS model outperforms ARIMAX in forecasting accuracy.
- HPI and CPI have a negative relationship.

## Abstract

This study aims to improve the predictive accuracy of the Housing Price Index (HPI) in India using the unrestricted MIDAS (U-MIDAS) model with novel predictors, including total digital payment value (TDP), consumer price index (CPI), and financial stress index (FSI). Quarterly HPI data from the Reserve Bank of India (RBI) and monthly data for other variables were used from October 2019 to September 2024. Correlation analysis indicates that HPI and digital payments are positively correlated. There is a weak relationship between HPI and FSI. HPI and CPI have a negative relationship. The U-MIDAS model outperformed other models. The study highlights the effectiveness of the U-MIDAS methodology for short-term forecasting. The study further demonstrates that the forecast accuracy obtained with the unrestricted mixed data sampling (U-MIDAS) regression exceeds that of the ARIMAX model.