Data Engineer: Prepare Financial Data for ML and Backtesting

Name: Data Engineer: Prepare Financial Data for ML and Backtesting
Rating: 4.6 (117 reviews)

Learn how to extract information out of standard financial data without writing any code using Crypto Wizards software.

Created byShaun McDonogh

Last updated 4/2022

English

English [Auto],

What you'll learn

Extract meaningful features out of mundane price and volume data for Machine Learning and Backtesting
Join data tables
Add time steps to your data
Automatically calculate correlation and cointegration
Add technical indicators within seconds
Add conditional features without needing excel
Filter your data table
Prepare your data for Machine Learning

Course content

5 sections • 16 lectures • 1h 23m total length

Introduction - The Power of Data Engineering10:51
Learn to extract actionable information from financial data using data engineering tools, RSI-driven features, and time-series prediction for backtesting-ready insights.
Data Extraction - Downloading and Viewing Data3:32
Learn how to extract financial data using data builder, rename and copy datasets, and view, download, or inspect the data with a view table before preparation for ML and backtesting.
Table Stats - Data Statistical Overview2:43
Review the table stats view to understand min, max, average, standard deviation, and percentile ranges for the data, enabling informed decisions about RSI, MACD, and moving averages.

Transform Features - Part 1 (Basics)4:36
Learn to use the transform features tool to delete, copy, rename, and apply log transforms to stock price columns, preparing financial data for machine learning and backtesting.
Transform Features - Part 2 (Returns)7:49
Transform features for machine learning by converting close price data into returns and related metrics (percent change, difference, move) using lookback to reveal volatility and actionable signals.
Transform Features - Part 3 (Time-steps)5:41
Add time-step features by capturing prior days' returns to create t-1, t-2, up to t-n columns and feed them into the machine learning model to capture sequence effects.
Transform Features - Part 4 (Joining Data)4:51
Learn how to join Nasdaq price data into your base dataset by matching date time, bringing in the close price to enrich features for ML and backtesting.
Transform Features - Part 5 (Correlation and Co-integration)7:35
Learn how correlation and co-integration reveal trading edge by analyzing spread, hedge ratio, and z-score to enable mean-reverting pairs trading, arbitrage, and backtesting insights.
Transform Features - Part 6 (Drop NA)1:40
Drop missing values in transform features to remove blanks from prior-day calculations, sacrificing some days but ensuring data quality for machine learning; check data integrity and consider zero imputation.

TA - Part 13:20
This module shows how to add technical indicators to financial time series, including 12-day, 21-day, and 100-day moving averages, using close prices, while warning about look-ahead bias in trend scanners.
TA - Part 25:44
Curate financial data for machine learning and backtesting by adding and removing indicators in the data builder, including daily log return, RSI, Bollinger bands, and moving averages.

Conditional Signals and Outcomes4:45
Learn to create conditional trading signals—long or short—using close price, 21-day moving average, RSI, and look-ahead targets, enabling binary classification for machine learning and backtesting.
Filtering Data2:39
Use the filter tool to keep data that meets a condition; filtered rows are removed, so backups matter, and focus on signals like moving average over close, RSI, and MACD.
ML Prep - Preparation for Machine Learning5:48
Upload football data, encode text fields into numbers with label or dummy encoding, and preview quick ML Trainer predictions for classification and regression.

End to End Walkthrough10:31
Learn to prep financial data end-to-end by building RSI-based features from S&P 500 data, labeling ten-day moves, and evaluating a time-series machine learning model with an 80/20 split for precision.
Congratulations and Closing Comments1:54
you engineered the right data and features, extracted insights, and built a strong dataset for machine learning and backtesting, gaining a market edge while mindful of overfitting.

Requirements

You will need to be a registered member with Crypto Wizards to use the features seen in this course

Description

After learning how to extract financial data using Data Builder, you will naturally be wondering how to make use of all the standard data you have pulled. In this course, you will learn how to structure data in such a way that seemingly mundane data can be transferred into useful information that can give you an edge in the financial markets.

Using Data Engineer, you will be able to:

Calculate returns in terms of values, percentages, differences and absolute moves (volatility)
Add time sequences to your data for predictions in machine learning
Add correlation and co-integration information comparing any columns/features for any assets
Add technical indicators
Add conditions for making predictions about the future
Add filters for removing unnecessary data
Prepare your features for machine learning (although not required for backtesting

You will be able to do all of this without writing a single line of code. However, you will need to be a registered member of Crypto Wizards to take advantage of this material as this course was built to teach users (as requested) how to use the platform. If you are not a registered member, you can still take valuable principles away from this course and perhaps code this yourself using Python or another data science related approach.

See you in class.

Who this course is for:

Retail traders and retail quants looking to gain an edge in the financial and crypto markets

Data Engineer: Prepare Financial Data for ML and Backtesting

What you'll learn

Explore related topics

Course content

Introduction - Getting Started3 lectures • 17min

Transforming Features6 lectures • 32min

TA - Technical Analysis2 lectures • 9min

Conditions, Filters and ML Preparation3 lectures • 13min

Summary - Putting It All Together2 lectures • 12min

Requirements

Description

Who this course is for: