- Designed algorithm to obtain quantitative factors and established several different machine learning models, such as
- XGBoost, random forest and LightGBM, to predict the security price in high-frequency trading based on factors selected
- Selected securities that have similar trend in price to the target security within each period based on Euclidean Distance
J
Jinrong Investment
Data Engineer Intern
Chengdu, CN
March 2020 - August 2020
T
Texas A&M University
Research Assistant
College Station, TX, US
July 2019 - September 2019
Skills
Accounts PayableAlgorithmsAmplitudesAnacondaBiomedical EngineeringCausal InferenceComputer ProgrammingC++ (Programming Language)DatabasesDecodingDockerEncodingsFinancial SecuritiesFinancial StocksForecasting SkillsHigh-Frequency TradingInformation EngineeringKnowledge of EngineeringKnowledge of FinanceKnowledge of LeasingsKnowledge of StatisticsLaTeXMachine LearningMathematical OptimizationMATLABMicrosoft ExcelMicrosoft Visual StudioProbability and StatisticsProgramming ToolsPython (Programming Language)Quantitative ResearchRandom ForestRipple (payment Protocol)RStudioSafety PrinciplesSimulationsSQL DatabasesStatistical Hypothesis TestingStock MarketsSubsystemsSwap (finance)TeachingTime SeriesXgboost