AI for Trader from ZERO

1. Statistics – very basic

AI-from-ZERO-001

Provider: Udacity
Price: Free

(Optional)

AI-from-ZERO-002-descriptive statistics

Provider: Udacity
Price: Free

 

2. Intro to Computer Science (Optional, for non cs background students)

AI-from-ZERO-003-intro-to-cs

Provider: Udacity
Price: Free
Skill Level: Beginner

3. Programming Foundations with Python (Basic)

AI-from-ZERO-004-programming-foundations-with-py

Provider: Udacity
Price: Free
Skill Level: Beginner

4. Intro to Data Analysis

AI-from-ZERO-005-intro-to-data-analysis

Provider: Udacity
Price: Free
Skill Level: Beginner

5. Artificial Intelligence for Trading – Quantitative Trading

AI-from-ZERO-006-AI-for-trading-Quant-Trading

  • TIME
    2 Three-Month Terms

    Study 10 hrs/week and complete in 6 months

  • CLASSROOM OPENS
    November 20, 2018
  • PRICE
    £799 GBP
  • PREREQUISITES
    Python programming & Mathematics

 

6. Artificial Intelligence for Trading – AI Algorithms in Trading

(to be updated…)

Learn how to analyze alternative data and use machine learning to generate trading signals. Run a backtest to evaluate and combine top performing signals.

SEE FEWER DETAILS

3 months to complete
  • Sentiment Analysis with Natural Language Processing

    Learn the fundamentals of text processing, and analyze corporate filings to generate sentiment-based trading signals.

    SENTIMENT ANALYSIS USING NLP

  • Advanced Natural Language Processing with Deep Learning

    Learn to apply deep learning in quantitative analysis and use recurrent neural networks and long short-term memory to generate trading signals.

    DEEP NEURAL NETWORK WITH NEWS DATA

  • Simulating Trades with Historical Data

    Learn to refine trading signals by running rigorous back tests. Track your P&L while your algorithm buys and sells.

    BACKTESTING

  • Combining Multiple Signals

    Learn advanced techniques to select and combine the factors you’ve generated from both traditional and alternative data.

    COMBINE SIGNALS FOR ENHANCED ALPHA

     

 

 

Educational Objectives:  In this program, you’ll analyze real data and build  financial models for trading. Whether you want to pursue a new job in finance, launch yourself on the path to a quant trading career, or master the latest AI applications in quantitative finance, this program offers you the opportunity to master valuable data and AI skills.

Prerequisite Knowledge: In order to succeed in this program, we recommend that you have some experience programming with Python, and be familiar with statistics, linear algebra, and calculus.

If you are new to Python, check out our  free Intro to Data Analysis  course. If you feel that you need to refresh your  statistical and algebra knowledge, take a look at our  free statistics course, Intro to Statistics, and linear algebra course, Linear algebra refresher.

Length of Program: The program is comprised of 2 terms, lasting 3 months each. We expect students to work  10 hours/week on average. Make sure to set aside adequate time on your  calendar for focused work.

Instructional Tools Available: Video lectures, quizzes, Jupyter notebooks, personalized project reviews.

Nanodegree Program Information

Each term is comprised of 4 courses and 4 projects, which  are described in detail below. Building  a project is one of the best ways  to demonstrate the skills you’ve learned, and each project will contribute to an impressive professional portfolio that shows potential employers your  mastery of quantitative finance.

Length of Program (months): Two three-month terms, total of six months

Number of terms: Two

Estimated time/week: 10 hours/week

Number of Reviewed Projects: 8

Projects

Building  a project is one of the best ways  to both test the skills you’ve acquired and to demonstrate your newfound abilities to future employers. Throughout this Nanodegree program, you’ll have the opportunity to master valuable skills by building the following projects:

 

Term 1: Quantitative Trading

  • Project 1: Trading with Momentum
  • Project 2: Breakout Strategy
  • Project 3: Smart Beta and Portfolio Optimization
  • Project 4: Multi-factor Model

Term 2: AI Algorithms for Trading

  • Project 5: Sentiment Analysis using NLP

  • Project 6: Deep Neural Network with News Data

  • Project 7: Backtesting

  • Project 8: Combine Signals for Enhanced Alpha

 

In the subsequent sections, you’ll find a description of each project, along with the lesson content you’ll learn along the way.

TERM 1: QUANTITATIVE TRADING

In the first term, you’ll learn the basics of quantitative analysis, from data processing and trading signal generation to portfolio management. You will use Python to work  with historical stock data, develop trading strategies, and construct a multi-factor model with optimization.

Project 1: Trading with Momentum

In this project, you will learn to implement a momentum trading strategy and test if it has the potential to be profitable. You will work  with historical data of a given stock universe and generate a trading signal  based on a momentum indicator. You will then compute the signal  and produce projected returns. Finally, you will perform a statistical test to conclude if there is alpha in the signal.

Course: Basic Quantitative Trading

In this course, you will learn about market mechanics and how  to generate signals with stocks. Your first project is to develop a momentum trading strategy.

Lesson content

  • Lesson 1: Introduction
  • Lesson 2: Stock Prices
  • Lesson 3: Market Mechanics
  • Lesson 4: Data Processing
  • Lesson 5: Stock Returns
  • Lesson 6: Momentum Trading

Project 2: Breakout Strategy

In this project, you will code and evaluate a breakout signal. You will run  statistical tests to test for normality and to find alpha. You will also  learn to find outliers and evaluate the effect that filtered outliers could have on your  trading signal.  You will run  various scenarios of your  model with or without the outliers and decide if the outliers should be kept or not.

Course: Advanced Quantitative Trading

In this course, you will get to know  the workflow that a quant follows  for signal  generation, and also  learn to apply advanced quantitative methods in trading.

Lesson content

  • Lesson 1: Quant Workflow
  • Lesson 2: Outliers and Filtering Signals
  • Lesson 3: Regression
  • Lesson 4: Time Series Modeling
  • Lesson 5: Volatility
  • Lesson 6: Pairs Trading and Mean Reversion

 

Project 3: Smart Beta  and Portfolio Optimization

In this project, you will create two portfolios utilizing smart beta methodology and optimization.  You will evaluate the performance of the portfolios by calculating tracking errors. You will also  calculate the turnover of your  portfolio and find the best timing to rebalance. You will come up with the portfolio weights by analyzing fundamental data, and by quadratic programming.

Course: ETFs, Indices, Stocks

In this course, you will learn about portfolio optimization, and financial securities formed by stocks such as market indices, vanilla  ETFs, and Smart Beta ETFs.

Lesson content

  • Lesson 1: Stocks, Indices and Funds
  • Lesson 2: ETFs
  • Lesson 3: Portfolio Risk and Return
  • Lesson 4: Portfolio Optimization

 

Project 4: Multi-factor Model

In this project, you will research and generate multiple alpha factors. Then you will apply various techniques to evaluate the performance of your  alpha factors and learn to pick the best ones for your  portfolio. You will formulate an advanced portfolio optimization problem by working with constraints such as risk models, leverage, market neutrality and limits on factor exposures.

Course: Multi-factor Model

In this course, you will learn about alpha factors and risk factors, and construct a portfolio with advanced portfolio optimization techniques.

Lesson content

  • Lesson 1: Factors Models of Returns
  • Lesson 2: Risk Factor Models
  • Lesson 3: Alpha Factors
  • Lesson 4: Advanced Portfolio Optimization with Risk and Alpha Factors Models

 

TERM 2: AI ALGORITHMS FOR TRADING

In this term, you will work  with alternative data and use machine learning to generate trading signals. You will run  a backtest to evaluate your  signals and use advanced techniques to combine the top performing signals.

Project 5: Sentiment Analysis  using NLP

In this project, you will apply Natural Language Processing on corporate filings, such as 10Q and 10K statements, from cleaning data and text processing, to feature extraction and modeling. You will utilize bag-of-words and TF-IDF to generate company-specific sentiments.  Based on the sentiments, you will decide which  company to invest in, and the optimal time to buy or sell.

Course: Sentiment Analysis  with Natural Language Processing

In this course, you will learn the fundamentals of text processing and use them to analyze corporate filings and generate sentiment-based trading signals.

 

Project 6: Deep Neural Networks with News  Data

In this project, you will build  deep neural networks to process and interpret news data. You will also  play with different ways  of embedding words into vectors. You will construct and train LSTM networks for sentiment classification. You will run  backtests and apply the models to news data for signal  generation.

Course Advanced Natural Language Processing with Deep Learning

In this course, you will get to know  how  deep learning is applied in quantitative analysis and get to use Recurrent Neural Networks (RNN) and Long Short-Term Memory Networks (LSTM) to generate trading signals.

 

Project 7: Backtesting

In this project, you will construct open-high-low-close (OHLC) data feed and a backtesting framework. You will learn about various visualization techniques for backtesting. You will construct trading strategies using various parameters such as trade days, take profit levels, stop loss  levels, etc. You will then optimize the parameters and evaluate the performance by analyzing the results of your  backtests.

Course: Simulating Trades with Historical Data

In this course, you will learn to refine trading signals by running a rigorous backtest. You will know  how  to keep track of your  P&L while your  algorithm buys and sells.

 

Project 8: Combine Signals  for Enhanced Alpha

In this project, you will create a prediction model for S&P 500 and its constituent stocks by performing model selection for a large data set which  includes market data, fundamental data and alternative data. You will validate your  model to ensure there is no overfitting. You will rank and select stocks to construct a long/short portfolio based on the prediction results.

Course: Combining Multiple Signals

In this course, you will learn about advanced techniques to select and combine the factors that you’ve generated from both alternative data and market data.