The basic Vector Autoregression (VAR) model is heavily used in macro-econometrics for explanatory purposes and forecasting purposes in trading. In recent years, a VAR model with time-varying parameters has been used to understand the interrelationships between macroeconomic variables. Since

Reinforcement learning (RL) is one of the most exciting areas of Machine Learning, especially when applied to trading. RL is so appealing because it allows you to optimise strategies and enhance decision-making in ways that traditional methods can’t. One of its biggest advantages? You don’t have

Statistical arbitrage is a classic quantitative trading strategy, and pairs trading is one of them. Digital currency perpetual contracts are non-delivery perpetual futures. This project describes using data from the Binance exchange to find perpetual contract pairs whose pairing spreads conform to

Usually, regime detection is made with an HMM estimation over price returns or price return volatility. However, Chen and Tsang (2021) propose to use the Directional Change indicators as input for a HMM to detect regime shifts. They show that the HMM applied to the Directional Change indicators

XGBoost…!!!! Often considered a miraculous tool embraced by machine learning enthusiasts and competition champions, XGBoost was designed to enhance computational speed and optimise machine learning model’s performance. Let's proceed with XGBoost!!! We will cover the following things: Brief

Whenever you want to estimate a model for multiple time series, the Vector Autoregression (VAR) model will serve you well. This model is suitable for handling multiple time series in a single model. You will learn here the theory, the intricacies, the issues and the implementation in Python and R.

Usually, in algorithmic trading, we talk about AutoRegressive Integrated Moving Average (ARIMA) models. They’re very popular in the industry. You might remember that the “d” component in the model can be 0, 1, 2, etc. What if 'd' could take fractional values? We’ll learn about such

In the AutoRegressive Moving Average (ARMA) models: A Comprehensive Guide of my ARMA article series, I covered the theoretical aspects of Autoregressive Moving Average models (ARMA). In the AutoRegressive Moving Average (ARMA) models: Using Python, I simulated different ARMA models, their

In the first part of my ARMA article series, I covered the background theory of lag operators, the stationarity and invertibility of Autoregressive Moving Average models (ARMA) and the different types of versions you can create from it. Here, we’ll explore theoretically these models using Python.

Machine Learning (ML) has emerged as a powerful tool in the field of Artificial Intelligence, revolutionising various aspects of our lives. Whether it's recognising human handwriting or enabling self-driving cars, ML has become an integral part of our daily routines. With the exponential growth

Autocorrelation is a statistical concept that measures the correlation between observations of a time series and its lagged values. It is commonly used in various fields, including trading for technical analysis, to identify patterns, trends, and relationships within data. Autocorrelation helps

Generally, a quant is a professional in the financial technology industry who designs complex algorithms with the help of quantitative analysis. Quants are skilled in mathematics, finance, and computer skills. In the trading domain, quants design and implement algorithms to predict the price and

“The intelligent investor is a realist who sells to optimists and buys from pessimists.” - Benjamin Graham Sentiment Trading strategies work on market sentiment and the trends around them. The strategies are often determined by the price and value of an asset that may fluctuate. Market

Algorithmic Trading is seeing a rapid expansion of the application of artificial intelligence (AI) and machine learning (ML). These technological developments have completely transformed Algo trading. Making informed decisions requires carefully analyzing both current and historical market data. In

As the name suggests, long short equity strategy is one where we take both long and short positions in different equities. This strategy is normally used by hedge funds to generate greater risk adjusted returns due to its inherently low risk characteristics. In this article, you will learn about how

Start learning all about the Dijkstra algorithm for finding the shortest path. We briefly review the Kruskal algorithm, Prim algorithm, Johnson algorithm and Bellman algorithm as well. We'll cover: What is the Dijkstra algorithm? How does the Dijkstra algorithm work? Pseudo code of Dijkstra

This is the second installment of my series on regression analysis used in finance. In the first installment, we touched upon the most important technique in financial econometrics: regression analysis, specifically linear regression and two of its most popular flavours: univariate linear

Machine learning is a need in almost every sector today. Sectors like medicine, transportation, healthcare, advertising and financial technology are tremendously reliant on machine learning. Speaking about the financial technology domain, algorithmic trading practice is extremely efficient with the

Are you looking to get stock market data and analyse the historical data in Python? You have come to right place. After reading this, you will be able to: Get historical data for stocks Plot the stock market data and analyse the performance Get the fundamental, futures and options data For easy

In the previous blogs, we examined supervised learning algorithms like linear regression in detail. In this blog, we look at what unsupervised learning is and how it differs from supervised learning. Then, we move on to discuss some use cases of unsupervised learning in investment and trading. We

Contrary to a more developed market, arbitrage opportunities are not readily realised which suggests there might be opportunities for those looking and able to take advantage of them. This project focuses on China's futures market using Statistical Arbitrage and Pair trading techniques. This

Zipline is a fantastic tool for backtesting and data is the main raw material for doing this kind of analysis. In this post, we are going to focus on how to load our own data files. Through an example, we will create a bundle to load data from csv files downloaded from Yahoo finance.

With the abundance of raw data and the need for analysis, the concept of unsupervised learning became popular over time. The main goal of unsupervised learning is to discover hidden and exciting patterns in unlabeled data. The most common unsupervised learning algorithm is clustering. Applications

Time series modelling is a very powerful tool to forecast future values of time-based data. Time-based data is data observed at different timestamps (time intervals) and is called a time series. These time intervals can be regular or irregular. Based on the pattern, trend, etc. observed in the past

Data cleaning is the time-consuming but the most important and rewarding part of the data analysis process. The process of data analysis is incomplete without cleaning data. But what happens if we skip this step? Suppose we had certain erroneous data in our price data. The incorrect data formed

Technical analysis of price and volume history won’t cut it alone nowadays. When we want to perform value investing and/or measure a security’s intrinsic value, we need to make a fundamental analysis of the security. To perform fundamental analysis we need data, lots of data. We want fundamental

As a quant trader, you are always on the lookout to create and optimise your trading strategies. Backtesting forms a very important part of this process. And for backtesting, access to historical data is a necessity. But it’s a very daunting task to find decent historical price data for

Is it possible to predict where the Gold price is headed? Yes, let’s use machine learning regression techniques to predict the price of one of the most important precious metal, the Gold. Machine Learning in Trading We will create a machine learning linear regression model that takes information

In Finance and Trading, a large amount of data is generated every day. This data comes in the form of News, Scheduled Economic releases, employment figures, etc. It is clear that the news has a great impact on the prices of stocks. Every trader takes great efforts in keeping track of the latest news

In this article, we will study a deep learning framework based on recurrent neural networks to predict daily equity index price movements. Specifically, the focus will be on long short-term memory (LSTM) networks - which are a type of recurrent neural network. Different types of inputs and network

The first quarter of 2020 has been one of the most challenging times in the post World War II era. The crash in oil prices due to geopolitical reasons and the COVID-19 global pandemic were the dominant themes. Financial markets act as bellwethers and give us a reflection of the overall sentiment for

In this post, we will learn about Markov Model and review two of the best known Markov Models namely the Markov Chains, which serves as a basis for understanding the Markov Models and the Hidden Markov Model (HMM) that has been widely studied for multiple purposes in the field of forecasting and

In the last blog, we examined the steps to train and optimize a classification model in scikit learn. In this blog, we bring our focus to linear regression models. We will discuss the concept of regularization, its examples(Ridge, Lasso and Elastic Net regularizations) and how they can be

When you are completely immersed in wanting to learn something new, you start looking for everything that surrounds the learning process. And with the aspiration to learn Algorithmic Trading, there must be certain questions crowding your mind, like: How do I learn Algorithmic Trading? What are the

Since predicting the future stock prices in the stock market is crucial for the investors, Time Series and its related concepts help in organizing the data for accurate prediction. In this article, we are focusing on Time Series, its analysis and forecasting. In this article, we aim to cover the

With the advent of several machine / deep learning models, there have been several theories emerging in applying these techniques for stock market prediction because of the difficulty and complexity it involves. In this project, we’re trying to solve the problem using a classifier to predict

As trading becomes automated, we have seen that traders seek to use as much data as they can for their analyses. But we all know that adding more variables leads to more complications and that in turn might make it harder to come to solid conclusions. Think about it, we have more than 3000 companies

Years ago, I had made it to the final round in an interview for a Senior Delta One/Quantitative Futures position at an HFT firm (unnamed for privacy). Things were going well, I had answered two out of three of those ridiculous questions that are only applicable in Subsaharan Africa or Finance

The automated trading system or Algorithmic Trading has been at the centre-stage of the trading world for more than a decade now. A “trading system”, more commonly referred as a “trading strategy” is nothing but a set of rules, which is applied to the given input data to generate entry and

In this project, we analyze different intraday trading strategies with Pivot Points. After defining different ways of calculating the Pivot Point, we do a Backtest with the most classic strategies and a different variant to those normally taught in textbooks. To learn about Pivot Point and how to

In the market, it is crucial to spot the trend, but it is equally important to detect when the trend ends. Getting out of the trade is more difficult than entering the trade. In this blog, we will talk about one such technical indicator, the Parabolic SAR indicator, which helps in identifying when

Support Vector Machines were widely used a decade back, but now they have fallen out of favour. The below data from google trends can establish this more clearly. (Source: Google Trends) Why did this happen? As more and more advanced models were developed, support vector machines fell out of favour.

Pairs trading is supposedly one of the most popular types of trading strategy. In this strategy, usually a pair of stocks are traded in a market-neutral strategy, i.e. it doesn’t matter whether the market is trending upwards or downwards, the two open positions for each stock hedge against each

Scikit-learn is one of the most versatile and efficient Machine Learning libraries available across the board. Built on top of other popular libraries such as NumPy, SciPy and Matplotlib, scikit learn contains a lot of powerful tools for machine learning and statistical modelling. No wonder scikit

A stop-loss order, or stops as is generally said, is an order placed with the broker to sell (or buy) if the stock of a company which you hold, reaches a pre-determined price in order to avoid large losses. In the trading world, the use of stops is seen as an essential part of risk control and money

In recent years, machine learning, more specifically machine learning in Python has become the buzz-word for many quant firms. In their quest to seek the elusive alpha, a number of funds and trading firms have adopted to machine learning. While the algorithms deployed by quant hedge funds are never

From showing related articles at the end of the article you have browsed through to creating a personalised recommendation based on your viewing habits, you would be surprised of the number of times you have been interacting with the K-means algorithm without even realising it. The above examples

You are probably wondering how a technical topic like Neural Network Tutorial is hosted on an algorithmic trading website. Neural network studies were started in an effort to map the human brain and understand how humans take decisions but algorithm tries to remove human emotions altogether from the

In this article, we will understand how natural language processing, sentiment analysis and social media play a role in the share markets with the help of Python. This would be explained with respect to the trading in China markets A-share stocks. This article is the final project submitted by the

Decision trees are often used while implementing machine learning algorithms. The hierarchical structure of a decision tree leads us to the final outcome by traversing through the nodes of the tree. Each node consists of an attribute or feature which is further split into more nodes as we move down