Shulou(Shulou.com)06/01 Report--

This article mainly introduces "what are the common packages of R language quantitative investment". In the daily operation, I believe that many people have doubts about what are the common packages of R language quantitative investment. The editor consulted all kinds of materials and sorted out the simple and easy-to-use operation methods. I hope it will be helpful for you to answer the doubts of "what are the common packages of R language quantitative investment?" Next, please follow the editor to study!

1. Why use R language to make quantitative investment?

What are the advantages of R to make quantitative investment? The most important point is that the R language is supported by many third-party packages. Usually, programming languages are designed to solve the problems of software development and program implementation. But at the beginning, R language was designed to solve data problems. Quantitative investment is a variety of data processing, data analysis, so as to find the law of the data. Therefore, there are many people engaged in quantitative investment, using R language to build quantitative transaction models, back testing, risk management and so on, and finally open source and contribute the research results to the R language community, which is of great help to the people behind.

Compared with Python, there are also a lot of third-party package support, most of which provide Web development, data crawlers, system management, database calls, mathematical computing, etc., these are general software requirements, not the data requirements of an industry. When a certain Python god begins to focus on the field of quantitative investment and implements a set of quantitative libraries with Python, the people behind will enter the field and just follow the route of the big god, waiting for the next big god to appear. So in essence, Python is a programming-oriented language, while R is a data-oriented language.

R language has been accumulated for many years in the field of quantitative investment, and many algorithms have been formed. From investment research to transaction analysis, and then to risk management, there is a complete architecture. We can also follow the path of our predecessors, learn quickly and quickly build a quantitative investment system. For people with IT but lack of financial knowledge, it is difficult to get started with a lot of knowledge. At the same time, they do not understand all kinds of statistical indicators, which causes great resistance to learning. In fact, this is the problem that you will face when you go deep into a specific industry. Industry knowledge and mathematical knowledge is the most difficult, only a breakthrough, you can open up new areas of cognitive methods.

R language brings us closer to data, provides a variety of mathematical statistical tools, and has a large number of industry knowledge bases contributed by third parties, so I will choose R language, and I will use R language as the best tool for quantitative investment analysis.

two。 Commonly used quantitative investment toolkit

R language provides a lot of financial computing frameworks and tools in the financial field. When you have financial theoretical knowledge and market experience, you can use the technical framework provided by these third parties to build your own financial model. We can find various financial items on CRAN, visit R's official website (https://cran.r-project.org/)), and find the Finance tag in the Task Views menu (URL: https://cran.r-project.org/web/views/Finance.html).

The financial field covers a wide range of areas, including banking, insurance, trust, securities, leasing and so on. The financial industry has the characteristics of index, monopoly, high risk, benefit dependence and high debt management. Quantitative investment is a very subdivided professional field of securities investment, and there are not many financial toolkits involved. As a matter of fact, once we can study these toolkits, we can easily do quantitative models and transactions.

If we want to use R to build our own quantitative trading system, you need to use five R language toolkits: data management, index calculation, backtest trading, portfolio, and risk management.

Data management: including dataset crawling, storage, reading, time series, data processing, etc. The R packet includes zoo (time series object), xts (time series processing), timeSeries (Rmetrics time series object) timeDate (Rmetrics time series processing), data.table (data processing), quantmod (data download and visualization), RQuantLib (QuantLib data interface), WindR (Wind data interface), RJDBC (database access interface), rhadoop (Hadoop access interface), rhive (Hive access interface), rredis (Redis access interface). Rmongodb (MongoDB access interface), SparkR (Spark access interface), fImport (Rmetrics data access interface) and so on.

Index calculation: various calculation methods including technical indicators of financial markets The R package includes TTR (technical index), TSA (time series calculation), urca (unit root test), fArma (Rmetrics ARMA calculation), fAsianOptions (Rmetrics Asian option pricing), fBasics (Rmetrics calculation tool), fCopulae (Rmetrics financial analysis), fExoticOptions (Rmetrics option calculation), fGarch (Rmetrics Garch model), fNonlinear (Rmetrics nonlinear model), fOptions (Rmetrics option pricing), fRegression (Rmetrics regression analysis). FUnitRoots (Rmetrics unit root test) and so on.

Backtest transactions: including financial data modeling, and verifying the reliability of the model with historical data, involving R package including FinancialInstrument (financial products), quantstrat (strategic model and backtesting), blotter (account management), fTrading (Rmetrics trading analysis) and so on.

Portfolio: manage and optimize multi-strategy or multi-model, including PortfolioAnalytics (portfolio analysis and optimization), stockPortfolio (stock portfolio management), fAssets (Rmetrics portfolio management), etc.

Risk management: calculation of risk indicators and risk prompts for positions, including PerformanceAnalytics (risk analysis), fPortfolio (Rmetrics portfolio optimization), fExtremes (Rmetrics data processing) and so on.

Based on the R packets listed above, we can choose to use independent third-party R packets to build our quantitative transaction system, or we can choose a complete Rmetrics system to build a quantitative trading system. These two types of R packets can also be mixed, and if when mixing, because the underlying objects of the time series they are based on are different, then you need to take some effort to deal with the type conversion.

The R language listed above is not all R packages for quantifying investment in R language, just some packages that I focus on. There are many others, such as the package PairTrading; for pairing trading, which was released on Github. the R packet that I didn't find.

For myself, I tend to use independent third-party R packets to do quantitative trading systems, several of which are independent R packets. There are two main reasons for this choice. First, the Chinese market is relatively special, and many rules do not fully meet world standards. For example, the trading of the stock Troup1 is the only one in the world. Another point is the third-party open source package, some may have errors, so you should not rely entirely on the third-party package, to have independent thinking and judgment, the third-party package only provides us with convenience.

Then the common combinations of third-party R packages are: zoo, xts, TTR, quantmod, FinancialInstrument, quantstrat, blotter, PortfolioAnalytics, PerformanceAnalytics. Any of these packages can be replaced or implemented on their own, thus ensuring the uniqueness of their own quantitative trading system. Quoting a picture in foreign quantitative textbooks, foreign countries use R to study the quantitative transaction system.

At this point, the study of "what are the common packages for quantifying investment in R language" is over. I hope to be able to solve your doubts. The collocation of theory and practice can better help you learn, go and try it! If you want to continue to learn more related knowledge, please continue to follow the website, the editor will continue to work hard to bring you more practical articles!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.