Jason Voorhees
π―ππ― ππππ π΅πππππ
- Joined
- May 15, 2020
- Posts
- 56,542
- Reputation
- 155,686
Since niggas accused me of making rep farms and posting gore all the time. Here is a high IQ high effort thread from me. Let's start with prerequisites to start quantitative analysis
What you'd need. A strong math background. You need advanced atleast graduate level knowledge on
-Probability
-Linear algebra
-Calculus 1 and 2
-Time series analysis.
So if you are uncomfortable with math or not good with numbers to put it bluntly don't bother because you'd have 0 clue what is going on and end up losing a shit ton of money.
Software to run the algorithms. Python is the most common. You'd also need to Install these libraries
-numpy, pandas - Helps in Data handling.
-matplotlib, seaborn-To visualize data
-scipy.stats- gives you ready-made functions.
'yfinance - To Download stock market data.
β’ TA-Lib - To compile technical indicators.
backtrader, zipline-For backtesting trading strategies.
You also need have a full understanding of stocks options bonds, portfolio theory and market microstructure.
A good book I'd recommend for this would be. Quantitative Trading by Ernest Chan.
Now for quantitative analysis
Step-1
Get historical stock data from Yahoo Finance/Alpha Vantage/ Quandl. Market data is often incomplete or contains errors. This data can be filled through various functions in the pandas libraries. Z Score methods etc. Won't get into too kuch detail if you are good with math you already know all of this
Step 2
This is the trickiest part. You need to analyze trends & patterns in the market. You can use moving averages Bollinger Bands, and momentum indicators to identify profitable
setups. The most commonly used ones are
-Descriptive statistics :Mean, median, standard deviation. If you studied high school math you should be knowing this.
-Correlation & Regression: Identifies the relationships between stocks. Same applies high school math.
-Moving Averages: SMA, EMA which Simple Moving Average and EMA stands for Exponential Moving Average. It sounds complicated but if you studied Time series analysis in college. You should be knowing this
-Volatility Analysis: ATR, Bollinger Bands.. ATR is Average True Range and Bollinger Bands. ATR focuses on the average price movement while Bollinger Bands use standard deviation from a moving average to create bands around the price like in those stock market charts. You need to study them
Once you have Identifies patterns and have found profitable setups you can go to developing a strategy
Step 3:
Develop a Trading Strategy. The most common ones are
-Mean Reversion: Buy low, sell high.
-Momentum Trading: Follow the trend.
-Pairs Trading: Exploit correlated stocks. You calculate the Pearson correlation coefficient between stock pairs to identify strong positive or negative correlations. A correlation above 0.8 suggests a strong relationship.
There are also more advanced Trading strategies that people use but since you are starting. I'd only recommend you to follow one of these three
Step 4
Testing. I can't stress this enough. You need to always test your strategy on past data to see if it would have worked because history repeats itself niggers. Some useful statistics to look at would be Sharpe Ratio, max drawdowns, and risk-adjusted returns. You can use chatgpt to understand what exactly these things are
Step 5
Use machine learning to enhance predictions. Run your strategies thorough an ML software with deep learning algorithms like neural networks, LSTMs etc. Again won't go too much in depth because you can write an entire book on these things alone
Step 6
It is now finally time to Deploy & Trade Live. You can use broker APIs like Alpaca to execute trades automatically. Use python scripts and api calls to place orders Start with paper trading a few times before going live.
Step 7
Monitoring. Use web hooks and other applications to monitor your stocks and get notifications. You can get the codes for these on chatgpt
Now, since some faggots will call me jewish shill and ask me why I am not a millionaire doing this. No I haven't done quantitative analysis myself because I frankly don't have the patience for this and I do have a life outside of crunching number everyday. I simply dont have the mental capacity to grind this hard with no clear payoff. Many people spend years refining their strategies and the competition is brutal, specially in fields like high-frequency trading and financial derivatives.
If you don't enjoy constantly crunching numbers debugging code and refining models dont look in this direction. Some quants do make insane amounts of money, but most either burn out, fail. It is a deep rabbit hole, you can spend years doing all of this and still not get good at it. Quantitative Analysis is too time consuming and head breaking for me but hey if you think you have 0 social life and have some insanely genius strategy that would work and are high IQ enough maybe you can struck gold with this. Good luck!
What you'd need. A strong math background. You need advanced atleast graduate level knowledge on
-Probability
-Linear algebra
-Calculus 1 and 2
-Time series analysis.
So if you are uncomfortable with math or not good with numbers to put it bluntly don't bother because you'd have 0 clue what is going on and end up losing a shit ton of money.
Software to run the algorithms. Python is the most common. You'd also need to Install these libraries
-numpy, pandas - Helps in Data handling.
-matplotlib, seaborn-To visualize data
-scipy.stats- gives you ready-made functions.
'yfinance - To Download stock market data.
β’ TA-Lib - To compile technical indicators.
backtrader, zipline-For backtesting trading strategies.
You also need have a full understanding of stocks options bonds, portfolio theory and market microstructure.
A good book I'd recommend for this would be. Quantitative Trading by Ernest Chan.
Now for quantitative analysis
Step-1
Get historical stock data from Yahoo Finance/Alpha Vantage/ Quandl. Market data is often incomplete or contains errors. This data can be filled through various functions in the pandas libraries. Z Score methods etc. Won't get into too kuch detail if you are good with math you already know all of this
Step 2
This is the trickiest part. You need to analyze trends & patterns in the market. You can use moving averages Bollinger Bands, and momentum indicators to identify profitable
setups. The most commonly used ones are
-Descriptive statistics :Mean, median, standard deviation. If you studied high school math you should be knowing this.
-Correlation & Regression: Identifies the relationships between stocks. Same applies high school math.
-Moving Averages: SMA, EMA which Simple Moving Average and EMA stands for Exponential Moving Average. It sounds complicated but if you studied Time series analysis in college. You should be knowing this
-Volatility Analysis: ATR, Bollinger Bands.. ATR is Average True Range and Bollinger Bands. ATR focuses on the average price movement while Bollinger Bands use standard deviation from a moving average to create bands around the price like in those stock market charts. You need to study them
Once you have Identifies patterns and have found profitable setups you can go to developing a strategy
Step 3:
Develop a Trading Strategy. The most common ones are
-Mean Reversion: Buy low, sell high.
-Momentum Trading: Follow the trend.
-Pairs Trading: Exploit correlated stocks. You calculate the Pearson correlation coefficient between stock pairs to identify strong positive or negative correlations. A correlation above 0.8 suggests a strong relationship.
There are also more advanced Trading strategies that people use but since you are starting. I'd only recommend you to follow one of these three
Step 4
Testing. I can't stress this enough. You need to always test your strategy on past data to see if it would have worked because history repeats itself niggers. Some useful statistics to look at would be Sharpe Ratio, max drawdowns, and risk-adjusted returns. You can use chatgpt to understand what exactly these things are
Step 5
Use machine learning to enhance predictions. Run your strategies thorough an ML software with deep learning algorithms like neural networks, LSTMs etc. Again won't go too much in depth because you can write an entire book on these things alone
Step 6
It is now finally time to Deploy & Trade Live. You can use broker APIs like Alpaca to execute trades automatically. Use python scripts and api calls to place orders Start with paper trading a few times before going live.
Step 7
Monitoring. Use web hooks and other applications to monitor your stocks and get notifications. You can get the codes for these on chatgpt
Now, since some faggots will call me jewish shill and ask me why I am not a millionaire doing this. No I haven't done quantitative analysis myself because I frankly don't have the patience for this and I do have a life outside of crunching number everyday. I simply dont have the mental capacity to grind this hard with no clear payoff. Many people spend years refining their strategies and the competition is brutal, specially in fields like high-frequency trading and financial derivatives.
If you don't enjoy constantly crunching numbers debugging code and refining models dont look in this direction. Some quants do make insane amounts of money, but most either burn out, fail. It is a deep rabbit hole, you can spend years doing all of this and still not get good at it. Quantitative Analysis is too time consuming and head breaking for me but hey if you think you have 0 social life and have some insanely genius strategy that would work and are high IQ enough maybe you can struck gold with this. Good luck!
Last edited:
