Let’s carry out the quantitative analysis of the market for the last 15+ years to define what portfolios have more stability and outperform the market.

There is no code, but a lot of graphs. If you want to play with your data or tweak the parameters you can do it here in Google Colab. The entire experiment is fully reproducible and doesn’t need the developer environment, all you need is a web browser.

*No investment advice. The content of the article is for informational and research purposes only.*

Passive investments involve periodic stock purchases and infrequent rebalancing of the portfolio…

Today we talk about a technique that allows searching a good set of parameters for a limited time, also we will consider one trading strategy as a bonus. Have a good read!

**Gentle Introduction to Particle Swarm Optimization****Trading Strategy Algorithm****Let’s Code It!****Experiment****Further Improvements****Summary**

The main goal of the optimization for our task is to define the sub-optimal parameters of the trading strategy **that maximize or minimize the objective function** (usually it uses the minimization).

The objective function could be simple like the return of the algorithm that we should maximize or the drawdown that we…

The market data is a sequence called time series. Usually, researchers use only price data (or asset returns) to create a model that forecasts the next price value, movement direction, or other output. I think the better way is to use more data for that. The idea is try to combine versatile market conditions (volatility, volumes, price changes, and etc.)

The first type of potential features are the various derivatives of price data. The second type is the set of the volume derivatives.

These features will describe the current market condition more complex than raw market data or simple returns.

…

Today we are going to create an ML model that forecasts the price movement in the order book. This article contains a full-cycle of research: getting data, visualization, feature engineering, modeling, fine-tuning of the algorithm, quality estimation, and so on.

An order book is an electronic list of buy and sell orders for a specific security or financial instrument organized by price level. An order book lists the number of shares being bid or offered at each price point, or market depth. Market depth data helps traders determine where the price of a particular security could be heading. For example…

Algorithmic trading has similar problems to those in machine learning. Today, I’m going to show how to apply Bayesian optimization for tuning trading strategy hyperparameters.

Let’s suppose you created a trading strategy with a few hyperparameters. This strategy is profitable on a backtesting. You want to deploy the strategy to production mode, but there is one question left: “Is this set of parameters optimal?”.

Typically, a grid-search approach is used to search for optimal hyperparameters. This approach is also used in machine learning, but this requires a lot of computations, often in the wrong parameter space.

Another approach is a…

The article describes a brief introduction to pairs trading including concept, basic math, strategy algorithm, trading robot development, backtesting and forwarding tests evaluation, and future problems discussion. As a practical example, the robot will trade on cryptocurrencies.

Pairs trading is a market-neutral trading strategy that employs a long position with a short position in a pair of highly co-moved assets.

The strategy’s profit is derived from the difference in price change between the two instruments, rather than from the direction each moves. Therefore, a profit can be realized if the long position goes up more than the short, or the…

Today I’m going to show how to create an algorithmic trading strategy on Python. This strategy uses my original research from one previous article. This current article consists of these parts:

- Concept
- Algorithm description
- Trading strategy development
- Backtesting and analyzing the result
- Further problems discussion
- Conclusions

Financial time-series have a high level of noise in data. Would be good to have an ability to reduce a noise. In this article it is proposed to use Renko brick size optimization. The key idea of the approach is to quantify the quality of a Renko chart and try to get an optimal…

The global stock market has a wide range of various Exchange Traded Funds (ETFs). Today we are going to compare a random portfolio management of stocks and ETF investing. Hundreds of random investors will be simulated. We will try to understand is there a difference between these approaches.

All operations will be carried out in R.

An ETF, or exchange-traded fund, is a marketable security that tracks an index, a commodity, bonds, or a basket of assets like an index fund. Unlike mutual funds, an ETF trades like a common stock on a stock exchange. …

I’ve been developing once an analytical tool for analyzing the Russian stock market. The purpose was building CAPM for stocks that are included in RTSI. I carried out this analytical pipeline in R: data recieving, CAPM calculation, and chart drawing. It was implemented as R script. I periodically launched this script to apply in an investment decision-making. It looked something like this:

This project had been solving a problem, but it was a little inconvenient. First of all, it needs R environment. The main issue is data manipulation, such as changing a period of analysis, ordering of a result, and…

Hi everyone!

I carry out research on financial time series at Quantroom. We work on algorithmic strategies problems in stock and crypto markets. Today, I’m going to overview a research about how to do a noise reduction in financial time series using Renko chart. The purpose of the article is an answer to this question **“Is there an approach that is better than the well-known ones to determine an optimal brick size?”**.

Renko chart is chart type that is only concerned with price movement, time and volume are not included. Renko chart doesn’t show each price movement. …

Data science & Quantitative finance http://malchevskiy.pro