廣宣學堂: R programming for_quantitative_finance_0623
4 likes720 views
This document provides an overview of using R for quantitative finance. It discusses R's history and popularity, basics of R including vectors, matrices, data frames and lists. It also covers exploratory time series analysis, stock trading strategies, correlation analysis, ARIMA modeling and forecasting, and querying the Bitcoin blockchain with R packages. The document is intended to introduce analysts to capabilities of the R programming language for financial applications.
![Fun Time –
What’s incorrect about subsetting
• Tsmc and foxconn columns
A. M_tsmc_foxconn[,c(“tsmc”, “foxconn”)]
B. M_tsmc_foxconn[c(“tsmc”, “foxconn”)]
C. M_tsmc_foxconn[,]
dsjerry2017@gmail.com](https://image.slidesharecdn.com/rprogrammingforquantitativefinance0623-170623161007/85/R-programming-for_quantitative_finance_0623-32-320.jpg)
![Present value( )
•
Cash / (1 + X /100) ^ Periods( )
Cash * (1 + X / 100) ^ -Periods( )
Chapter3_data_frame.R
dsjerry2017@gmail.com
1000 6%
839.62 [1000 / (1 + 6%)^3]
X =](https://image.slidesharecdn.com/rprogrammingforquantitativefinance0623-170623161007/85/R-programming-for_quantitative_finance_0623-39-320.jpg)
廣宣學堂: R programming for_quantitative_finance_0623
- 1. R Programming for Quantitative Finance (Jerry Wu)
- 2. (R & RStudio) quantmod forecast Rbitcoin igraph plyr
- 3. What is R • R is one of the most popular platforms for data analysis and visualization currently available. dsjerry2017@gmail.com
- 4. Some news about R http://spectrum.ieee.org/computing/software/the-2016-top-programming-languages dsjerry2017@gmail.com
- 5. A brief history of R Time Topic 1993 Research project in Auckland, NewZealand Ross Ihaka and Robert Gentlemen 1995 Released as open-source software Generally compatible with the ‘S’ language 1997 R core group formed 2000 R 1.0.0 released 2004 First international user conference in Vienna 2012 R 2.15.2 released 2013 R 3.0.2 released The CRAN package repository features 5,026 available packages. 2017 R 3.4.1 released The CRAN package repository features 10,875available packages.dsjerry2017@gmail.com
- 6. Data analysts captivated by R’s Power dsjerry2017@gmail.com
- 7. Why “R”? Not “SAS”? Or others? • 2009 • R (lingua franca) • Google, Microsoft, Facebook, Johnson & Johnson,Pfizer, Merck, BOA, InterContinental Hotels and Shell…, including New York Times now use it ! • • • • To give researchers of all stripes an accessible data analysis tool. • 10,875 (2017) dsjerry2017@gmail.com
- 8. R may be the disruptor ! dsjerry2017@gmail.com
- 9. The Tools We’re Using – Ranked by Usage • R is the tool used by the most data miners (70%) Rexer Analyticsdsjerry2017@gmail.com
- 10. The Popularity of R Software is Skyrocketing • 70% R • 24% R dsjerry2017@gmail.com
- 11. Discussion lists and sites dsjerry2017@gmail.com
- 12. KDnuggets Four of the top five packages were open source dsjerry2017@gmail.com
- 13. Hits on Google Scholar • Google R dsjerry2017@gmail.com
- 14. Why use R • (Free/open source software) • • • • • dsjerry2017@gmail.com
- 18. Outline • The Basics • Vectors and Matrices, Data Frames, Factors, Lists • Exploratory time series data analysis • Stock Trading • Quantitative Analysis • Correlation analysis • MA Model Estimation and Forecasting • Querying the Bitcoin blockchain with R dsjerry2017@gmail.com
- 19. Stock Returns • $90 worth of Foxconn Stock • 10% return in March • 110% = 100% + 10% • 1.10 = 1 + 0.10 • 99 = 90 * 1.10 + - Chapter1_stock_returns.R dsjerry2017@gmail.com
- 20. Stock Returns – Multiple periods • $90 worth of Foxconn Stock • 10% return in March • 110% = 100% + 10% • 1.10 = 1 + 0.10 • 99 = 90 * 1.10 • 5% return in April • 110% = 100% + 5% • 1.05 = 1 + 0.05 • 94.5 = 90 * 1.05 • 103.95 = 90 * 1.10 * 1.05 Chapter1_stock_returns.R dsjerry2017@gmail.com
- 21. Fun Time • $100 worth of Stock • 10% return in March • 5% return in April dsjerry2017@gmail.com
- 22. The Basics • Basic Data Types • Vectors and Matrices • Data Frames • Factors • Lists dsjerry2017@gmail.com
- 23. Basic Data Types • Numeric • Character • Logical Chapter1_stock_returns.R dsjerry2017@gmail.com
- 24. Basic Data Types • Variables and data types • Class() Chapter1_stock_returns.R dsjerry2017@gmail.com
- 25. The Basics • Basic Data Types • Vectors and Matrices • Data Frames • Factors • Lists dsjerry2017@gmail.com
- 26. Vector – Vectors and stock prices • Vectors and stock prices • Vector names() Chapter2_vectors_and_matrices.R dsjerry2017@gmail.com
- 28. Fun Time • Try • + – * / Chapter2_vectors_and_matrices.R dsjerry2017@gmail.com
- 32. Fun Time – What’s incorrect about subsetting • Tsmc and foxconn columns A. M_tsmc_foxconn[,c(“tsmc”, “foxconn”)] B. M_tsmc_foxconn[c(“tsmc”, “foxconn”)] C. M_tsmc_foxconn[,] dsjerry2017@gmail.com
- 33. Cor()relation • +1 perfect positive linear relationship • -1 perfect negative linear relationship • 0 no linear relationship Chapter2_vectors_and_matrices.R dsjerry2017@gmail.com
- 35. Visualize your matrix (Time Series) Chapter2_vectors_and_matrices.R dsjerry2017@gmail.com
- 36. The Basics • Basic Data Types • Vectors and Matrices • Data Frames • Factors • Lists dsjerry2017@gmail.com
- 37. Data Frames and Name that frame Chapter3_data_frame.R dsjerry2017@gmail.com
- 38. Data frame subsets and subset() Chapter3_data_frame.R dsjerry2017@gmail.com
- 39. Present value( ) • Cash / (1 + X /100) ^ Periods( ) Cash * (1 + X / 100) ^ -Periods( ) Chapter3_data_frame.R dsjerry2017@gmail.com 1000 6% 839.62 [1000 / (1 + 6%)^3] X =
- 41. Present value( ) • Fun Time ( 5%) 4 Chapter3_data_frame.R dsjerry2017@gmail.com
- 42. The Basics • Basic Data Types • Vectors and Matrices • Data Frames • Factors • Lists dsjerry2017@gmail.com
- 48. The Basics • Basic Data Types • Vectors and Matrices • Data Frames • Factors • Lists dsjerry2017@gmail.com
- 51. Fun time • 1 1000 ? Chapter5_list.R dsjerry2017@gmail.com
- 54. Data Input and output Chapter6_io.R dsjerry2017@gmail.com
- 55. Outline • The Basics • Vectors and Matrices, Data Frames, Factors, Lists • Exploratory time series data analysis • Stock Trading • Quantitative Analysis • Correlation analysis • MA Model Estimation and Forecasting • Querying the Bitcoin blockchain with R dsjerry2017@gmail.com
- 56. Exploratory time series data analysis • (Time Series) • GDP .. dsjerry2017@gmail.com
- 57. Exploratory time series data analysis • • dsjerry2017@gmail.com
- 58. Exploratory time series data analysis • • dsjerry2017@gmail.com
- 59. Exploratory time series data analysis • : , , • (Data Granularity) • : , , • dsjerry2017@gmail.com
- 60. Exploratory time series data analysis • • {yt } • (state space) S • (Discrete) • (Continuous) dsjerry2017@gmail.com
- 61. Exploratory time series data analysis • (index set) • • (Discrete) T={0,1,2……} • • (Continuous) T=[0, ∞) dsjerry2017@gmail.com
- 62. Exploratory time series data analysis Chapter7_EDA.R dsjerry2017@gmail.com
- 63. Exploratory time series data analysis 0501 0501 Chapter7_EDA.R dsjerry2017@gmail.com
- 65. Exploratory time series data analysis Chapter7_EDA.R dsjerry2017@gmail.com
- 66. Exploratory time series data analysis Chapter7_EDA.R dsjerry2017@gmail.com
- 67. Exploratory time series data analysis • Moving Average Convergence / Divergence, MACD DIF-MACD MACD DIF( ) Chapter7_EDA.R dsjerry2017@gmail.com
- 69. Basic Time Series Objects Chapter7_EDA.R dsjerry2017@gmail.com
- 70. Basic Time Series Objects Chapter7_EDA.R dsjerry2017@gmail.com
- 71. Outline • The Basics • Vectors and Matrices, Data Frames, Factors, Lists • Exploratory time series data analysis • Stock Trading • Quantitative Analysis • Correlation analysis • MA Model Estimation and Forecasting • Querying the Bitcoin blockchain with R dsjerry2017@gmail.com
- 73. Stock Trading • 20ma 60ma • 20ma 60ma ( ) Lag ROC log( / ) * Strategy (0,1) Cl OHLC cumsum exp Chapter7_EDA.R dsjerry2017@gmail.com
- 75. Outline • The Basics • Vectors and Matrices, Data Frames, Factors, Lists • Exploratory time series data analysis • Stock Trading • Quantitative Analysis • Correlation analysis • MA Model Estimation and Forecasting • Querying the Bitcoin blockchain with R dsjerry2017@gmail.com
- 78. Correlation analysis • Rapid Growth dsjerry2017@gmail.com
- 82. Correlation analysis Diff( ) Log( )(linearized) (Periodic) Chapter8_QA.R Diff 12 x 13 y =1+(y-x)/x dsjerry2017@gmail.com
- 83. Correlation analysis - Scatterplots Chapter8_QA.R dsjerry2017@gmail.com
- 84. Correlation analysis – correlation coefficient http://www.stat.nuk.edu.tw/prost/content2/statics_6.htm +1 0 -1 dsjerry2017@gmail.com
- 85. Correlation analysis – correlation coefficient P-value 0.05 df Chapter8_QA.R dsjerry2017@gmail.com
- 87. Outline • The Basics • Vectors and Matrices, Data Frames, Factors, Lists • Exploratory time series data analysis • Stock Trading • Quantitative Analysis • Correlation analysis • MA Model Estimation and Forecasting • Querying the Bitcoin blockchain with R dsjerry2017@gmail.com
- 88. MA Model Estimation and Forecasting • ARIMA Autoregressive Integrated Moving Average model, ) • ARIMA p d q • p • d TS • q • ARIMA ACF PACF p,d,q • ACF(Sample Autocorrelation Function, ) • PACF (Sample Partial Autocorrelation Function, ) ACF PACF Chapter8_QA.R dsjerry2017@gmail.com
- 89. MA Model Estimation and Forecasting Lag=1 Lag=3 arima(x, order = c(0,0,1)) arima(x, order = c(3,0,1)) AIC( ) (Goodness of Fit) AICChapter8_QA.R dsjerry2017@gmail.com
- 90. MA Model Estimation and Forecasting(Non-Auto ARIMA) Chapter8_QA.R dsjerry2017@gmail.com
- 91. MA Model Estimation and Forecasting(Non-Auto ARIMA) Chapter8_QA.R dsjerry2017@gmail.com
- 92. MA Model Estimation and Forecasting(Auto ARIMA) Chapter8_QA.R dsjerry2017@gmail.com
- 93. MA Model Estimation and Forecasting dsjerry2017@gmail.com
- 94. Outline • The Basics • Vectors and Matrices, Data Frames, Factors, Lists • Exploratory time series data analysis • Stock Trading • Quantitative Analysis • Correlation analysis • MA Model Estimation and Forecasting • Querying the Bitcoin blockchain with R dsjerry2017@gmail.com
- 96. Bitcoin • (Blockchain) • • 0.00000001 1 • 2140 2100 • = 90,375 https://zh.wikipedia.org/wiki/ dsjerry2017@gmail.com
- 97. Blockchain Blockchain is a distributed database that is used to maintain a continuously growing list of records, called blocks. Each block contains a timestamp and a link to a previous block. A blockchain is typically managed by a peer-to-peer network collectively adhering to a protocol for validating new blocks. https://medium.com/@micheledaliessi/how-does-the-blockchain-work-98c8cd01d2ae dsjerry2017@gmail.com
- 98. Querying the Bitcoin blockchain with R Chapter9_Blockchain.R dsjerry2017@gmail.com
- 99. Querying the Bitcoin blockchain with R Chapter9_Blockchain.R dsjerry2017@gmail.com
- 100. Conclusion • Concept of R basic • Exploratory time series data • Learn stock trading with R • Quantitative analysis with forecasting • Querying the Bitcoin Blockchain Visualization with R dsjerry2017@gmail.com