Pricing and hedging aggregated micro-loan cashflows

小额金融机构在为发展中国家和发达国家的大部分成年人提供资金方面发挥着关键作用。根据世界银行2017年的一份报告，世界三分之一的成年人口没有银行账户，因此依赖非正规经济中的小额信贷机构或贷款人获得信贷。鉴于小额信贷机构继续在社会福祉中发挥重要作用，它们必须掌握适当定制的数学工具，以量化和减轻向没有信用记录和没有抵押品的个人放贷业务带来的金融风险。本项目的目的是在考虑到小额贷款贷款人可能存在的具体限制(大量非常小额的贷款，没有抵押品等)的情况下，为一系列贷款制定定价和对冲金融衍生产品的数学公式。该项目将建立在两个不同的金融数学研究基础上：发达市场抵押贷款债券(CLO)的定价数学，以及最近利用机器学习在没有客户信用记录的情况下对小额贷款进行信用评分的工作。

Microfinance institutions (MFIs) play a critical role in providing access to capital to a large proportion of adult population in developing countries as well as in the developed world. According to a world bank report in 2017, a third of the world's adult population has no bank accounts and therefore rely on MFIs or lenders in informal economy for credit. Given the important role that MFIs continue to play in the wellbeing of society, it is imperative that they have appropriately tailored mathematical tools at their disposal for quantifying and mitigating financial risk posed by the business of lending funds to individuals with no credit history and no collateral. The purpose of this project is to develop mathematical formulation for pricing and hedging financial derivative products for a pools of loans, taking into account of specific constraints that microloan lenders might have (large number of very small loans, no collateral etc). The project will build on two different strands of research in financial mathematics: the mathematics of pricing Collateralized Loan Obligations (CLOs) in developed markets and recent work on credit scoring for microloans in absence of customer credit history, using machine learning