Weather data plays an imperative role in deciding the future prices of commodities and utilities, mainly energy prices. The studies measuring portfolio performances using financial data have mainly dominated the financial literature. The present paper is a different attempt to estimate the portfolio risks (portfolio VaR) for three of the city-wise, that is, Delhi, Mumbai, and Chennai monthly temperature data. Besides this, the portfolio risk capital was measured using point backtest method, thereby using traffic signal violations approach. To generate valuable results, it was important to use not just the historical values, but also randomly generated values for 191 monthly temperature figures. Along with this, conditional VaR accepting the maximum possible losses was also accommodated in the study. The use of GARCH 1, 1 model was attempted, which appears to be able to cover volatility clustering easily. The pure temperature portfolio risks and portfolio risk capital are accounted at different confidence intervals and this is the only scenario utilized for the analysis. With this extensive back-end analysis, the spreadsheet was utilized. This present paper is limited to the usage of temperature data of three cities (Delhi, Mumbai, and Chennai). For future research purposes, a greater number of cities and more weather parameters can be utilized. The banking sector, particularly financing to agricultural based projects, can make much use of such studies not only to safeguard itself against their investment portfolio, but can also use the findings from the present study (if permitted) to manage their capital adequacy requirements for mark-to-market trading portfolios. The results revealed the inter-city comparison of portfolio and individual VaR based risk capital estimations and also provide a model for researchers and practitioners to implement for further use.

1. Allen, D.E., Kramadibrata, A.R., Powell, R.J., & Singh, A.K. (2012). Conditional value at risk application to the global mining industry. Journal of Business and Policy Research, 7 (3), 11-23.
2. Campbell, S.D., & Diebold, F.X. (2005). Weather forecasting for weather derivatives. Journal of American Statistical Association, 100 (469), 6-16.
3. Feng, S. (n.d.). Establishing weather trading VaR using a bootstrap method. Retrieved from <a href=http://db.riskwaters.com/data/energyrisk/EnergyRisk/Energyrisk_0608/CuttingEdge_Jun08.pdf target="_blank">http://db.riskwaters.com/data/energyrisk/EnergyRisk/Energyrisk_0608/CuttingEdge_Jun08.pdf</a>
4. Pasquier, L. (2010). Sailing on the time-horizon: The closer,the better for VaR. Investment Acumen, AXA Investment Manager's Research Review, 9, 57-61.
5. Tarasov, A. (2011). Coherent quantitative analysis of risk in agribusiness: Cases of Ukraine. Agris on-line papers in Economics and Informatics, 3 (4), 2-4.
6. Taylor, J.W., & Buizza, R. (2006). Density forecasting of weather derivative pricing. International Journal of Forecasting, 22 (1), 29-42.
7. Vedenov, D.V., & Barnett, B. J. (2004). Efficiency of weather derivatives as primary crop insurance instrument. Journal of Agriculture and Resource Economics, 29 (3), 387-403.