own-research - QuantPedia

How to Paper Trade Quantpedia Backtests

November 18, 2022

Quantpedia’s mission is simple – we want to analyze and process academic research related to quant/algo trading and simplify it into a more user-friendly form to help everyone who looks for new trading strategy ideas. It also means that we are a highly focused quant-research company, not an asset manager, and we do not manage any clients’ funds or managed accounts. But sometimes, our readers contact us with a request to help them to translate strategy backtests performed in Quantconnect into paper trading or real-trading environment. The following article is a short case study that contains a few useful tips on how to do it.

Reviewing Patent-to-Market Trading Strategies

November 16, 2022

The following article is a short distillation of the research paper Leveraging the Technical Competence of a Stock for the Purpose of Trading written by Rishabh Gupta. The author spent a summer internship at Quantpedia, investigating the Patent-to-Market (PTM) ratio developed by Jiaping Qiu, Kevin Tseng, and Chao Zhang. The PTM ratio uses public information about the number and dates of patents assigned to publicly listed companies, calculates an expected market value of patents, and tries to predict future stock performance.

Impact of Dataset Selection on the Performance of Trading Strategies

November 14, 2022

It would be great if the investment factors and trading strategies worked all around the world without change and under all circumstances. But, unfortunately, it doesn’t work like that. Some of the strategies are market-specific, as shown in this short analysis. The Chinese market has its own specifics, mainly higher representation of retail investors and lower efficiency. And it’s not alone; countless strategies work just in cryptocurrencies, selected futures, or some other derivatives markets. So, what’s the takeaway? Simple, it’s really important to understand that each anomaly is linked to the underlying dataset and market structure, and we need to account for it in our backtesting process.

A Simple Approach to Market-Timing Strategy Replication

November 11, 2022

In previous articles, we discussed the ideas behind portfolio replication with market factors. However, overall robustness of the results suffers significantly if the model portfolio or trading strategy we attempt to synthetize is driven by a market-timing model. We do not know the rules driving the underlying strategy we could apply ourselves beforehand. Furthermore, there is no simple mechanism of market-timing rule detection we could potentially utilize in our regression model. Hypothetically, we could include a variety of market-timing strategies into the factor universe. But since there are countless market-timing methods, covering everything is simply unrealistic. Particularly in context of historic factor universe construction. In an attempt to capture the effects of underlying timing rules, we came up with a simple approach to address this problem to a somewhat satisfactory extent.

How to Replicate Any Portfolio

November 2, 2022

Would you like to see the performance of your portfolio 100 years back in history? Do you want to analyze the risk of your strategy under 100 years of real historical scenarios? All of these, and much more, will be soon (in a few days) available for Quantpedia Pro subscribers. How? We will explain today how we can model a 100-year history of your portfolio.

Introducing Quantpedia Answers

October 26, 2022

Approximately 18 months ago, when we started Quantpedia Pro service, we promised to systematically expand its analytical capabilities by adding new tools and reports to it. We kept this promise and enlarged Quantpedia Pro to over 30 reports with hundreds of tables and charts. Factor regression analysis, risk scenarios, seasonality analysis, alternative weighting schemes, risk parity, CPPI, volatility targeting, correlation analysis, Markowitz portfolio optimization, clustering, market phases analysis, ETF replication etc. offer insight into the matters of portfolio construction or risk management. But our disciplined tempo also means that some users can become lost in the number of tools Quantpedia Pro offers. Therefore, we would like to introduce to you our new Quantpedia Answers section, which contains practical examples of how to use the growing capabilities of Quantpedia Pro reporting.

How to Improve Post-Earnings Announcement Drift with NLP Analysis

October 11, 2022

Post–earnings-announcement drift (abbr. PEAD) is a well-researched phenomenon that describes the tendency for a stock’s cumulative abnormal returns to drift in the direction of an earnings surprise for some time (several weeks or even several months) following an earnings announcement. There have been many explanations for the existence of this phenomenon. One of the most widely accepted explanations for the effect is that investors under-react to the earnings announcements. Although we already addressed such an effect in some of our previous articles and strategies, we now present a handy method of improving the PEAD by using linguistic analysis of earnings call transcripts.

Multi Strategy Management for Your Portfolio

October 3, 2022

If you follow Quantpedia’s blogs, you probably know that Quantpedia PRO already contains multiple risk management and portfolio construction tools for your quantitative investment strategies. The newest Quantpedia PRO tool (available in a few days) will analyze something completely different, though – how to manage multi-strategy portfolios. The newest Quantpedia PRO tool (available in a few days) will analyze something completely different, though – how to manage multi-strategy portfolios. You can easily apply these multi-strategy overlays to various types of underlying – ETFs, systematic strategies, multi-asset portfolios, or multi-strategy portfolios. This article again serves as a primer for the new report’s methodology.

Automated Trading Edge Analysis

September 2, 2022

Have you ever wondered if your trading asset trends or mean-reverts? Everyone involved in trading or investments daily solves the task of – What trading strategy should I apply to my assets to generate profits? As always, we at Quantpedia will try to help you a bit with this never-ending task with our new tool/report, which will be unveiled next week for all Quantpedia Pro subscribers. The following article serves as an introduction to the methodology we will use to find new trading edges for you automatically.

100-Years of the United States Dollar Factor

August 16, 2022

Finding high-quality data with a long history can be challenging. We have already examined How To Extend Historical Daily Bond Data To 100 years, How To Extend Daily Commodities Data To 100 years, and How To Build a Multi-Asset Trend-Following Strategy With a 100-year Daily History. Following the theme of our previous articles, we decided to extend historical data of a new factor, the Dollar Factor. This article explains how to combine multiple data sources to create a 100-year daily data history for the Dollar Factor (the value of the United States Dollar relative to its most important trading partners’ currencies), introduces data sources, and explains the methodology.