Early Career Industry Fellowships - Grant ID: IE230100435
Funder
Australian Research Council
Funding Amount
$431,000.00
Summary
Customising weather index insurance for agribusiness using machine learning. This project aims to customise weather index insurance (WII) by utilising machine learning techniques. WII is used as a type of risk management tool in the agriculture sector to transfer risk due to extreme weather events. Significantly this project expects to establish an accurate correlation between insurance payouts and actual losses and thus improve the WII uptake rate. This will effectively support farmers and agri ....Customising weather index insurance for agribusiness using machine learning. This project aims to customise weather index insurance (WII) by utilising machine learning techniques. WII is used as a type of risk management tool in the agriculture sector to transfer risk due to extreme weather events. Significantly this project expects to establish an accurate correlation between insurance payouts and actual losses and thus improve the WII uptake rate. This will effectively support farmers and agribusinesses in Australia to mitigate and adapt to climate change, help reduce the impact of climate change and ensure crop production and food security.Read moreRead less
Limiting False Positives in Empirical Asset Pricing Tests. The project aims to address the issue of data mining in asset pricing tests using innovative interdisciplinary approaches that mitigate the occurrence of false positives. The expected outcomes include extended options in finance for alleviating data mining, as well as new guidelines for rigorously evaluating the explanatory power of risk factors on expected returns. The project findings are expected to significantly advance our understan ....Limiting False Positives in Empirical Asset Pricing Tests. The project aims to address the issue of data mining in asset pricing tests using innovative interdisciplinary approaches that mitigate the occurrence of false positives. The expected outcomes include extended options in finance for alleviating data mining, as well as new guidelines for rigorously evaluating the explanatory power of risk factors on expected returns. The project findings are expected to significantly advance our understanding of the pricing of risk. Additionally, the proposed tools are anticipated to have broad applications, such as corporate finance and fraud detection, and offer significant value to finance research and its stakeholders, such as the Australian asset management industry and government regulatory bodies.
Read moreRead less