“Quantitative investment” refers to the way that investors use mathematical analysis, computer programming technology, financial engineering modeling and other methods to find the relationship between the data through centralized comparison and processing of sample data, formulate quantitative strategies, and use written software programs to execute transactions, so as to obtain investment returns. Its core strength is its more accurate risk management and its ability to deliver excess returns. \
\
Quants are investors who use mathematical models to analyze financial markets and use complex mathematical formulas and computers to extract profits from fleeting market opportunities. In today’s quantitative investment field, there have been numerous model system software, in the powerful Python language and database support, quantitative investment is no longer a mysterious field.
\
Quantitative trading has become the mainstream of trading systems in major investment banks and hedge fund companies, and machine learning is also playing an important role in quantitative trading.
\
In order to help you to quantitative investment system learning
\
Lujiazui School
Invite the quant goddess at Morgan Stanley headquarters in New York
Introduced the Python | machine learning and quantitative trading, pricing of actual combat training (let)
This course aims to teach financial data processing and analysis, interest rate curve fitting, numerical solution of differential equations, quantitative trading and investment strategy modeling, and the application of machine learning in quantitative trading, and implement programmatic trading in Python code. Students can be familiar with Yahoo Finance Connection, SKLearn, QS Trader, StatsModel and other Python packages. In addition, the course will teach you quantitative job interview techniques to help you get your dream job offer.
\
Course objectives
\
1. Good command of Python
2. Master Python financial data processing and analysis skills
3. Basic quantitative trading strategy learning and Python implementation
4. Machine learning theory and Python implementation
5. Application of machine learning in quantitative trading and Python programmatic implementation
6. Master the pricing of Python derivatives
7. Teach job interview skills, improve your resume, how to win the job interview and get the offer of Dream Company
** ** Diana, Quantitative Finance division, Morgan Stanley New York Headquarters
Master’s degree in mathematical finance from New York University. She worked in the quantitative Finance department of Morgan Stanley New York headquarters, mainly engaged in algorithm trading, stock volume forecasting, machine learning research, fixed income and foreign exchange pricing modeling, and derivative pricing. Established interest rate and foreign exchange pricing model and stock statistical arbitrage model, sales and trading data for machine learning analysis has a unique research.
She established a systematic self-learning modeling framework for the important variables of the company’s trading book and provided guiding statistics for each quarter’s capital plan. In addition, kalman filter model and time series model are combined to predict large single trading volume and provide trading suggestions for traders. The convolutional neural network model is used to predict and learn the expected data of financial management and investment of the company’s high net worth customers, so as to provide quantitative guidance for the investment volume of the next year.
Diana also works as an interview director in her department, conducting interviews for candidates. Have a strong passion for sharing your own experiences and helping others succeed in their careers. She has 3 years of experience coaching student design internship programs in the United States, helping students perfect their resumes, prepare for interviews, and succeed in the finance industry.
Course content
Algorithmic Trading In Python Overview
Course Overview
1.what is algo-trading? Compare to retail traders
(What is quantitative trading for retail investors?)
2.why Python? Python notebook introduction
(Advantages of Python for quantitative trading)
3. Introduction to trading system
4.Python for finance commonly used packages: numpy, scipy, pandas, statsModel, sciKit-learn, matplotlib
(Use of Python in finance and various library functions)
5. Quantitative trading of employment analysis and career development
Python for Finance: Packages for Finance
1. Learn the basics of data analysis library — NumPy:
● Creating Arrays
Using Arrays and Scalars
Indexing Arrays
● Array Manipulation
● Array Functions
Library — Pandas
● DataFrames and file reading
(DataFrames and file reading import)
● Index and Reindex Objects, Index Hierarchy
(Index and index command object, index hierarchy)
● Select/Drop Entry
● Data Alignment, Rank and Sort, Handling missing Data
(Data alignment, ranking and sorting, handling missing data)
● Summary Statistics
3. Statistical analysis and optimization of Library-Scipy
● Optimization
● Statistical test
● Linear Algebra — LinalG
4. Drawing library – matplotlib
● How to plot basic graphs for different types
(How to draw basic graphics for different types)
● How to plot multiple graphs and do arrangement
(How to draw multiple figures and arrange them)
When the Advanced plotting
(Advanced graphics/Data Visualization)
Python for Finance (****packages
1. Statistical Model Library — StatsModel
Regression and generalized Regression models
(Regression and generalized regression models)
● Time series analysis
● Statistical test
● Distributions
2. Financial data processing
Frequency of data
● How to source data from Bloomberg, Yahoo Finance and so on
(How to get the source data)
● Data Quality Check and cleaning(smooth, seasonality Adjustment, filling-forward and so on)
Section 4 Financial data modeling and forecasting/risk measurement factors
1.Statistical learning and techniques overview
(Overview of Statistical Learning and Techniques)
2.Financial time series analysis
(Financial time series analysis)
3.Forecasting measures and techniques overview
(Overview of forecasting measures and techniques)
4.Performance evaluation and risk measures
(Performance measurement and risk measurement)
Section 5 traditional quantitative trading strategy and Python implementation
1.Event-driven trading strategies and implementation
(Event-driven trading strategy and implementation)
2. Statistical trading strategies and implementation
(Statistical trading strategy and implementation)
● Moving-Average Trade
● Pair trading
3. Parameter optimization
● Overfitting and cross-validation
● Grid Search
Section 6 I – Bayes model of high – order quantitative trading strategy
1.Advance algorithmic trading overview
(Overview of advanced algorithmic trading)
2. What is Bayesian statistics
(What is Bayesian statistics?)
3. Bayesian Inference methods
(Bayesian inference method)
4. Markov Chain Monte Carlo
(MCMC Markov Chain Monte Carlo)
5. Linear regression model based on Bayes
(Bayesian linear regression model)
6. Bayesian stochastic volatility model
(Bayesian stochastic wave model)
7. Python examples and model code implementation
Section 7 Financial Time Series Analysis-I
1. Sequence phase relation and random walk
(Random walk)
2. Stationary time series model -AR/MA/ARMA
(Volatility prediction model)
3. Non-stationary time series model-ARIMA/heteroscedasticity model-GARCH
Section viii. Financial Time Series Analysis -II
1.State-model and Kalman filter
(State model and Kalman filtering)
Low Kalman filter and found
(Kalman filter theory)
● Application to regression and pair trading in Python
(Application of Kaman filter in regression and paired transaction)
2.Hidden Markov Models
(Implicit Markov model)
HMM Theory
● Application to market regime detection in Python
(Application of HMM in market mechanism determination/detection)
Application of machine learning in Quantitative Trading I
1.Introduction to machine learning
(Introduction to machine learning)
2.Linear regression and MLE
(Linear regression and MLE)
3. The Decision Tree
Entropy and information gain theories
(Basis of entropy and information Theory)
● Pruning the tree
● Advanced tree Methods — Bagging, Boosting, Random Forest and Son on
(Advanced tree theory)
4. Python implementation
(How to do it in Python)
Section 10 Application of machine learning in Quantitative Trading II
1.Introduction to Support Vector Machine
(Introduction to Support Vector machines)
● Maximum margin classifier
Linear support vector Machine (SVM)
● Kernel function and higher dimension mapping
(Projection of kernel function and high dimensional data)
2. Cross-Validation for model selection
(Model selection for cross validation)
● Leave one out
Low K – a fold
● Bias-variance trade-off
Application of machine learning in Quantitative Trading III
1.Introduction to Clustering
(Introduction to cluster clustering)
Low Clustering and found
(Cluster theory clustering)
● Implementation to financial market
(Application in the financial field)
2. Neural network
(Neural network)
● Introduction to Artificial Neural Network
It has a recurrent neural network.
3. Unsupervised dimensional reduction techniques
(Unsupervised dimension reduction technique)
Low PCA/CCA
● Implementation to financial market
(Application in the financial field)
Application of machine learning in Quantitative Trading IV
1. Introduction to QS Trader in Python
QS Tader Overview
● QS Trader for Backtesting (using XXX backtesting)
2. ARIMA+GARCH Trading
(XXX transaction)
Strategy on Stock Market
What are the Indexes Using R?
3. Cointegration-Based Pairs Trading using QSTrader
(Qstrader-based collaborative integration/matching transactions under combination)
4. Kalman Filter-Based Pairs Trading using QSTrader
(QSTrader based Kaman Filter matching transaction)
5. Supervised Learning for Intraday Returns Prediction using QSTrader
(Predicting daytime trading returns using supervised learning)
Section 13 Python for ODE PDE Numerical Methods
1.ODE examples in Finance
(Ordinary differential equation finance example)
2.Forward Backward Crank-Nicholson Methods for ODE
(Forward and backward CN method)
3.Explicit Implicit and CN methods for PDE
(Explicit implicit CN method)
4.Option pricing examples for PDE
(Partial differential equation option pricing example)
Section 14 pricing Python Derivatives -I
1. Monte Carlo simulation foundation
2. Discretization of common stochastic processes
3. Monte Carlo simulation pricing of European Option
4. Exotic option
(Exotic option pricing)
5.Least-square monte-carlo for American option pricing
(Least square Monte Carlo for American option pricing)
Section 15 Pricing Python Derivatives -II
1.Common variance reduction techniques for Monte-Carlo and application to option pricing
(Common Monte Carlo Variance Reduction methods and Option Pricing)
2.Importance sampling and change of measure
(Key sampling order and measure changes)
3.Incremental risk charge model and Gaussian Copula for credit risk
(IRC model of credit risk and Gauss kernel)
Quant Job Interviews and Career Planning
How to effectively pass the interview and become an excellent quantitative analyst.
1.Quant job requirements and recruitment characteristics
2. Analyze the hiring process/job preparation schedule
How to prepare a resume with a high hit rate
4. Knowledge coverage points and how to prepare for an interview
5. Precautions for telephone and on-site interviews
\
\
This course is suitable for people
\
\
- Students/workers with financial engineering background would like to learn more about Python’s practical application in financial markets outside of the textbook
- Students/staff with non-financial engineering background want to have a systematic understanding of quantitative investment and its practical application in investment
- Professionals working in securities companies/funds/banks/futures companies/exchanges and other related fields want to further improve their competitiveness
- I hope to master the practical skills related to quantitative investment through the learning system, so as to prepare and improve the necessary knowledge and skills for the subsequent job-hopping/job-changing
\
Course registration
Long press below to identify the QR code
Or click to read the original text to register
