Analytics in Stock Markets Zoomcamp
[Started 15th April, you can still join] Spring 2024 cohort
In collaboration with DataTalks.Club
A gentle introduction to stock market trading, Python programming in Colab, analytics, and data visualisation
Course Syllabus
Understanding Data-Driven Decisions
- Explore the philosophy behind making decisions based on data.
- Delve into the landscape of potential personal investments.
- Address questions about where to focus attention and considerations of risk and reward.
- Guide you through setting up Colab for practical data analysis.
- Download your initial financial data using Finance APIs.
- Considerations for selecting the right API for your data needs.
- When it becomes necessary to consider payment options in the API selection process.
The Core Libraries for Data Analysis in Python
- Explore the core libraries: Numpy, Pandas, and Matplotlib (including Seaborn and Plotly Express).
- Delve into various data types: numeric, string, and date categories.
- Master the art of generating dummy variables for comprehensive analysis.
- Derive additional features such as hour/day of the week, growth over different periods.
- Incorporate technical indicators using the TaLib library.
- Understand predictive elements, including future growth over a week, a month, or a year.
- Learn strategies for cleaning and preparing data for analysis.
- Acquire skills in joining multiple datasets for a holistic view.
- Conduct a comprehensive descriptive analysis of the dataset.
- Explore correlations within the data to uncover meaningful insights.
Framing Hypotheses and Unraveling Time-Series Predictions
This week covers:
This week covers:
- Framing hypotheses for analytical exploration.
- Heuristics and hand rules for practical predictions.
- Predicting time-series data: trends, seasonality, and remainder decomposition.
- Regression techniques for understanding data relationships.
- Binary classification to determine growth direction.
- [Optional] Example of neural networks in analytical modelling.
Moving Beyond Prediction into the realm of Trading Strategy and Simulation
- [Optional] Explore screenshots of trading apps, guiding you on how to start—from downloading an app to placing a trade.
- Uncover key features of trading strategies, including considerations like trading fees, risk management, combining predictions, and timing of market entry.
- Delve into various strategy examples:
- Single stock investment for a long-term approach.
- Diversified portfolio optimisation for long investments in multiple stocks.
- Market-neutral strategies, involving both long and short positions based on predictions.
- Mean reversion strategy, driven by events.
- Vertical stocks covering and pairs trading.
- Exploration of "Penny" stocks and dividend strategies.
- [Maybe - Advanced] Basic options strategy.
- Simulate the financial results based on predictions and the chosen strategy.
Streamlining Processes from Prediction to Action
- Transition from Colab notebooks to Python files for improved deployment and execution.
- Establish persistent storage mechanisms, including files and potentially a simple SQLite database with an introduction to SQL.
- Explore automation techniques such as scheduling cron jobs for a series of .py files and consider data workflow solutions like Apache Airflow.
- Learn to generate predictions and execute trades systematically.
- [Maybe - Advanced] Implement automated email notifications containing predictions, trade details, and updates on profit/loss for the designated period.
Applying Analytical Skills in a Real-world Scenario
In the concluding weeks of the course, you'll embark on a comprehensive Capstone Project, applying the skills acquired throughout the program. This project aims to showcase your proficiency in data analysis, predictive modeling, and the implementation of trading strategies.
In the concluding weeks of the course, you'll embark on a comprehensive Capstone Project, applying the skills acquired throughout the program. This project aims to showcase your proficiency in data analysis, predictive modeling, and the implementation of trading strategies.
Why join?
Zero barriers to start
We use Google Colab notebooks. It is a copy-past solution, one-click init environment, and easy to extend.
No need to have a finance background
We explain our ideas with a plain language without complicated models and assumptions from theoretic finance.
Build a semi-automatic trading system
You'll create a set of notebooks with your ideas that can be applied for any broker account.
Make unbiased decisions
You'll try to validate the hypothesis at scale: from one example to hundreds of stocks observed.
Collaboration
Working in pairs and talking to like-minded people interested in investing, analysis, and programming.
Confident trading
You'll get a minimum working knowledge to generate your ideas and test them on the market.
Who should attend?
We believe the most common use cases are:
• Home traders and individual investors seeking a macro view of the market and the development of statistical intuition.
• Students looking to enhance their coding skills and tackle mathematical challenges in financial markets.
• Analysts or developers interested in trading, offering a brief introduction to the financial markets.
• Analysts aiming to acquire coding skills, with opportunities to practice web scraping, time-series analysis, and predictive modelling on extensive datasets.
• Students looking to enhance their coding skills and tackle mathematical challenges in financial markets.
• Analysts or developers interested in trading, offering a brief introduction to the financial markets.
• Analysts aiming to acquire coding skills, with opportunities to practice web scraping, time-series analysis, and predictive modelling on extensive datasets.
Prerequisites
For this course, it's recommended to have:
• An analytical mindset and the ability to make decisions based on data.
• Basic coding skills, ideally in a modern programming language (especially Python).
• Some background in trading or a keen interest in financial markets to apply the knowledge immediately.
• Previous experience in any of DataTalks.Club courses is beneficial.
• Basic coding skills, ideally in a modern programming language (especially Python).
• Some background in trading or a keen interest in financial markets to apply the knowledge immediately.
• Previous experience in any of DataTalks.Club courses is beneficial.
Format of a course
• Weekly live YouTube sessions will cover new material.
• Lecture materials will include sample code examples for your reference.
• Home exercises will be given to reinforce the covered content.
• Each section concludes with a questionnaire for submitting your homework.
• Final weeks will be devoted to a Capstone project and peer review
• Lecture materials will include sample code examples for your reference.
• Home exercises will be given to reinforce the covered content.
• Each section concludes with a questionnaire for submitting your homework.
• Final weeks will be devoted to a Capstone project and peer review
Results
By the end of the course, you will
• Discover new ways to check facts automatically on a large scale.
• Use Python to gather, test, and visualise the data, as well as create personalised trading algorithms.
• Connect with peers who share similar interests and can help you achieve better, long-lasting results.
• Discover new ways to check facts automatically on a large scale.
• Use Python to gather, test, and visualise the data, as well as create personalised trading algorithms.
• Connect with peers who share similar interests and can help you achieve better, long-lasting results.
[Course Registration] Spring 2024 cohort - start in April
Please fill in your details in the form (~5 minutes)
Analytical Blog articles
Explore the recent research algorithms, including interactive charts and code on the Github
Reach Out
Follow me
Sign up for our newsletter to get the latest news
