By Rishikesh Mahadevan Imagine you have to backtest a strategy on 50 stocks and for that you have to download price data of 50 stocks. But traditionally you have to download ticker by ticker. This sequential download process can be painfully slow, especially when each API call requires waiting for external servers to respond. What … Read more
By Manusha Rao Pre-requisites for learning from this blog: https://blog.quantinsti.com/python-programming/ https://blog.quantinsti.com/set-up-python-system/ https://blog.quantinsti.com/python-data-structures/ https://blog.quantinsti.com/python-data-types-variables-tutorial/ Level of your blog: Intermediate Here is a table with the Python libraries for a quick look. Python libraries Python is widely used to develop trading algorithms due to its extensive ecosystem of libraries tailored to finance and trading. In this article, … Read more
By Ishan Shah, Rekhit Pachanekar and Gaurav Singh Pre-requisite blogs: Level of this blog: Foundation/Beginner Technical indicators are calculated using historical price and volume data to predict the market direction. These indicators are added on charts using which you can set your entry and exit signals. Won’t it be amazing if you can compute these … Read more
By José Carlos Gonzáles Tanaka The ARFIMA model is well suited for capturing long-range memory in financial time series. However, it’s not always the case the time series exhibits long memory in their autocorrelation. The ARTFIMA model comes to the rescue to capture not only the long memory but also its short one and the … Read more
On February 4, 2025, SEBI introduced a circular aimed at making algorithmic trading safer and more transparent—especially for retail investors. This is a notable shift, as algo trading was primarily the domain of institutional players in the past. With these new guidelines, SEBI intends to broaden retail participation while maintaining strict risk controls. Key Highlights … Read more
By Rekhit Pachanekar You know that machine learning can be broadly categorised into supervised and unsupervised learning. Supervised learning uses labelled data, where the model learns from input-output pairs to make predictions or classifications. On the other hand, unsupervised learning works with unlabeled data to discover hidden patterns or structures. For instance, it can group … Read more
In the context of autoregressive (AR) models, the coefficients represent the weights assigned to the lagged values of the time series to predict the current value. These coefficients capture the relationship between the current observation and its past values. The goal is to find the coefficients that best fit the historical data, allowing the model … Read more
By Varun Pothula About Varun:Varun Pothula is a Quantitative Analyst at QuantInsti. He along with Rajib Ranjan Borah and Euan Sinclair has played a key role in curriculum creation of options trading module for EPAT. Varun’s academic credentials include a Master’s in Financial Engineering from WorldQuant University and a Bachelor’s in Mechanical Engineering from Vellore … Read more
By José Carlos Gonzáles Tanaka Imagine yourself, a great retail trader with an algorithm that flawlessly predicts stock movements for months—until a surprise Fed rate hike sends markets into chaos. Overnight, the model’s accuracy plummets. Why? Concept drift: your model no longer finds patterns in historical data and now underperforms its predictions. For machine-learning-based traders, … Read more
By Rekhit Pachanekar The origin of the Relative Strength Index (RSI) indicator is quite interesting. Created in 1986 by J. Welles Wilder, who was an engineer, land developer first and then a commodities trader, the RSI indicator has come a long way since its origin. Even though J. Welles Wilder was working on commodities when … Read more