Manager Machine

*

LINGYAN CAO

Quantitative Analyst/Econometric Modeler Email: **********.***@*****.***

International Monetary Fund Phone: 240-***-****

address: **** ******** **. *** ***. Hyattsville, MD 20782 SUMMARY

Ph.D. in Applied Mathematics in Finance with outstanding academic records, 6+ years’ working experience in machine learning, financial modeling, derivative pricing and term structure models forecasting, strong quantitative background in mathematics and statistics, as well as extensive client facing experience. PROFESSIONAL SKILLS

● PROGRAMMING: Python, Matlab, SQL, SAS, C#, R, oop, C++, open source library (numpy, pandas, sklearn, tensorflow)

● QUANTITATIVE: stochastic calculus, statistics, regression analysis, optimization, probability theory, numerical analysis, Monte Carlo Simulation, hypothesis testing, applied multivariate statistics

● QUANTITATIVE FINANCE: stochastic calculus, martingale, Black Scholes model, interest rate models, time series, derivative pricing, options, bonds, fixed income, VaR, jump process, Variance Gamma correlated process, Nelson Siegel model, CIR, HJM, Hull White model, Greeks.

● MACHINE LEARNING: statistical modeling, regression analysis (linear, logistic, lasso, ridge), classification (logistic, SVM, KNN), decision tree, random forests, gradient boosting methods, clustering (k-means, hierarchical), neural network, deep learning (convolutional neural network

(CNN), recurrent neural network (RNN))

EDUCATION

University of Maryland at College Park College Park, MD Ph.D. in Applied Mathematics in Finance June, 2011 Nanjing University Nanjing, China

B.S. in Computational Mathematics June, 2005

WORKING EXPERIENCE

International Monetary Fund, Washington D.C.

Quant Analyst/Econometric Modeler Sep. 2011 - Current

● Lead research projects focusing on technical implementation of advanced financial modelling methodologies

● Main contributor of machine learning training courses to IMF economists, with extensive exercises and projects implemented in python

● Participate in and lead a variety of projects in machine learning

● Design, main develop and publish several IMF in-house tools, as well as provide daily support SELECTED PROJECTS

Debt Manager

*Keywords: term-structure model, yields, bonds, borrowing policy, simulation

● Quantitatively studied the Government bond yields with CIR and Nelson-Siegel Model and term- structure forecasting.

● Computed bond prices and risk indicators based on current market yields.

● Simulated bond portfolio values and borrowing policy by calibrating a term-structure model for each currency.

2

Data Oriented IMF Member Country Segmentation

* Keywords: multi-class classification, softmax

● Built a sovereign ranking system of IMF member countries on various indices according to facts in different categories.

● Built a multi-class classification model using multi-layer neural network to predict the indices of unranked countries based on human ranked countries Forecasting Government Bond Yields with Nelson Siegel Model

* Keywords: Nelson Siegel Model, Maximum Likelihood estimation

● Quantitatively studied the Government bond yields with 3-factor Nelson-Siegel Model and term- structure forecasting.

● Estimated the three factors level, slope and curvature in 3 factor Nelson Siegel using 10 years’ monthly yields data of many IMF member countries

● Produced long-run forecasts to term-structures which is much more accurate than various standard benchmarks.

Financial Systemic Risk Analysis by Machine Learning

*Keywords: feature selection, penalized linear regression

● Modelled the country systemic risk by a portfolio of its corporates individual idiosyncratic risks. Priced the idiosyncratic risk by Greeks and volatility.

● Selected top 10 most influential corporates by penalized linear regression algorithm.

● Estimated future Greeks and volatility through geometric Brownian motion and forecasted the country’s systemic risk.

Contact this candidate