Machine Learning for Trading Profitably - AlgoJi

Machine Learning for Trading Profitably

40,000.00

By the end of this course, you should be able to:

  1. Understand different classes of quantitative trading strategies
  2. Know how to construct a machine learning pipeline
  3. Understand 3 popular machine learning algorithms and how to apply them to trading problems
  4. Understand how to assess a machine learning algorithm’s performance for time series data (stock price data)
  5. Know how and why data mining (machine learning) techniques fail
  6. Construct a stock trading software system that uses current daily data

In the interest of time, we will NOT be going into any mathematical equations, formulations or derivations in this course. This course is designed from a Practitioner’s perspective

Trainer Profile: Mr. Hrishabh Sanghvi

Hrishabh was head for Algorithmic Trading and DMA at Edelweiss for 6 years, one of India’s largest Financial Services company. He is CS Engineer and IIM Lucknow alumni. He is also Guest Faculty for NISM, IIML and BSEI. He is known to teach machine learning in a very easy and practicaly way.

This course has been sold out.

Out of stock

Category:

FAQs

1. For whom is this course useful?
  1. Anyone who wants to learn the quantitative side of trading & investment strategies.
  2. Anyone who wants to give to boost to his career by building a strong foundation in machine learning and data analysis

2. Will you help me with the pre-requisites for taking machine learning for trading course?

We have already given you links with some of the best tutorials on python. Also, python is the most popular language right now. So, you can google for any questions you are facing about it.

Special time from trainer to teach Python is not required and dilutes the objective of the course. Similarly, you are expected to be familiar with High School/Graduation 1st year level statistics during the course.

3. For what duration do I have access to recording?

Minimum 6-months after the course ends

4. Is the course online or offline? How will I learn?

It’s online 10-week course which starts 4th July. Classes will be held Wednesdays and Sundays, at 8:30 pm and 12 noon respectively (UTC 3 pm and 6:30am). Discount offer (30K instead of 40K) is valid only upto 21st June. Classes will be delivered through online virtual classroom. You don’t need to install any software to attend class, it will be accessible from smartphone also.

5. Do I get a good strategy? How profitable are the strategies you will discuss?

No holy-grail and no money minting schemes please! We cannot guarantee that you will start making money from trading immediately after this course. However, you can look at trainer’s profile, and go through detailed curriculum to make a wise decision.

5. Even more FAQs are covered in the session below. If you have more questions, email us on support@algoji.com

Curriculum

10-week course starts 4th July. Classes will be held Wednesdays and Sundays, at 8:30 pm and 12 noon respectively (UTC 3 pm and 6:30am). Discount offer is valid only upto 21st June

Introduction to Quantitative Trading Strategies (2 sessions)

  • Introduction – You, This Course & Us!
  • Are markets efficient or inefficient?
  • Introduction to quantitative trading strategies– o Long-only o Factors
    • Momentum
    • Mean Reversion o Arbitrage
    • Statistical Arbitrage o Events o Market Making o Scalping o Asset Allocation
  • Asset classes and timeframes for trading – What works in each?
  • Where do the opportunities lie?
  • Project: Installing Pycharm – a Python IDE

Machine Learning (3 sessions)

  • What is Machine Learning?
  • How to define a Machine Learning problem correctly?
    • Regression vs Classification vs Reinforcement o Linear vs non-linear
  • Common mistakes- o Overfitting o Data Insufficiency o Data Leakage o Non-stationary Distributions o Solving the wrong problem o Outliers o Linearity
  • How to avoid the common mistakes?
    • Hold out o Cross Validation o Boot strapping o Learning curves o Data visualization o ‘Active learning’ o Outlier detection
  • The Machine Learning pipeline
  • Framework for choosing the right ML model
  • Demo: Piotroski F-Score vs Machine Learning

Data Preparation (2 sessions)

  • The power of numpy
  • Code Along – Data Preparation
  • Adjusting for Corporate Actions
  • Data Sanity and Scrubbing
  • Incomplete data
  • Reading and Plotting stock data
  • Beautiful graphs with seaborn
  • Histograms and scatterplots
  • Statistical analysis of time series
  • Project: Data visualization and analysis for stock data

Feature Engineering (2 sessions)

  • Know the basics – A Pandas tutorial
  • Playing with Pandas dataframes
  • Constructing some simple features
  • Constructing a Momentum Feature
  • Constructing a Jump Feature
  • Engineering a Categorical Variable
  • Evaluating features o Correlations & Causality o Mutual Information o ReliefF
  • How to improve bad features?
  • Project: Feature engineering for momentum trading strategy

Feature Selection (2 sessions)

  • The problem of too many features
  • Feature selection algorithms o Filter vs Wrapper vs Embedded o Fast Correlation based Feature Selection o Joint Mutual Information o Genetic Algorithm based Wrapper
  • How to evaluate a feature selection method?
  • Optimal feature sets
  • Project: Run Feature selection on your engineered features

Decision Trees, Ensemble Learning & Random Forests (2 sessions)

  • Introducing Scikit-Learn
  • Planting the seed – What are Decision Trees?
  • Growing the Tree – Decision Tree Learning
  • Branching out – Information Gain
  • Decision Tree Algorithms
  • Project: Filtering out your Bad trades
  • The Wisdom Of Crowds – Ensemble Learning
  • Ensemble Learning continued – Bagging, Boosting & Stacking
  • Random Forests – Much more than trees
  • A Nearest Neighbors Classifier
  • Project: Train a ML model on your feature subset

Evaluating a Machine Learning Model (2 sessions)

  • Model parameters and hyper parameters
  • Parameter tuning approaches
  • Training & Testing – How to do it right?

Compare Results from different models – Objective functions and evaluation metrics        Project: Parameter Tuning for Gradient Boosted Classifiers

Prerequisites and Requirements

Students should have some coding skills and some familiarity with equity markets.

No finance or machine learning experience is assumed.

Note that this course serves students focusing on computer science, as well as students in other major such as industrial systems engineering, management, or math who have different experiences. All types of students are welcome!

The ML topics might be “review” for CS students, while finance parts will be review for finance students.
However, even if you have experience in these topics, you will find that we consider them in a different
way than you might have seen before, in particular with an eye towards implementation for trading.
Programming will primarily be in Python. We will make heavy use of numerical computing libraries like NumPy and Pandas.

Pre-lecture Study

Step 1: Learn the basics of Python language
Specifically learn: Lists, Tuples, Dictionaries, List comprehensions, Dictionary comprehensions
Assignment: Take the interactive Python tutorial by DataCamp: https://www.datacamp.com/courses/intro-to-python-for-data-science

Step 2: Learn Basic libraries in Python
Practice the NumPy tutorial thoroughly, especially NumPy arrays. This will form a good foundation for things to come http://wiki.scipy.org/Tentative_NumPy_Tutorial

Secondly, let us look at Pandas. Pandas provide DataFrame functionality (like R) for Python. This is also where you should spend good time practicing. Pandas would become the most effective tool for all mid-size data analysis. Start with a short introduction, 10 minutes to pandas. Then move on to a more detailed tutorial on
pandas http://www.gregreda.com/2013/10/26/intro-to-pandas-data-structures/

Check out DataCamp’s course on Pandas Foundations https://www.datacamp.com/courses/pandas-foundations

Assignment: Solve this assignment from CS109 course from Harvard

Step 3: Learn Scikit-learn
Scikit-learn is the most useful library on python for machine learning. Here is a brief overview of the library https://www.analyticsvidhya.com/blog/2015/01/scikit-learn-python-machine-learning-tool/

Career Benefits

Note that this is the first course in India discussing trading use-cases for ML, delivered by one of top quants in India. The first benefit is that you will get niche knowledge at the fraction of a price you need to pay for international courses.

You will recieve a certificate for completing this course.

The knowledge gained in this course will help you build solid foundation in maching learning. It will be helpful not only in trading, but also in different domains. You may consult your office HR also for value delivered and reimbursement for this course.

Get a call back

Fill the form below to get a call back regarding this course
  (Unlicensed)