High Probability Credit Spreads – Using Linear Regression Curves

Posted on September 29, 2013 by GekkoQuant

I came across this video series over the weekend, an option trader discusses how he trades credit spreads (mainly looks for mean reversion). Most of you will be familiar with bollinger bands as a common mean reversion strategy, essentially you take the moving average and moving standard deviation of the stock. You then plot on to your chart the moving average and an upper and lower band(moving average +/- n*standard deviations).

It is assumed that the price will revert to the moving average hence any price move to the bands is a good entry point. A common problem with this strategy is that the moving average is a LAGGING indicator and is often very slow to track the price moves if a long lookback period is used.

Video 1 presents a technique called “linear regression curves” about 10mins in. Linear regression curves aim to solve the problem of the moving average being slow to track the price.

Linear Regression Curve vs Simple Moving Average

See how tightly the blue linear regression curve follows the close price, it’s significantly quicker to identify turns in the market where as the simple moving average has considerable tracking error. The MSE could be taken to quantify the tightness.

How to calculate the linear regression curve:

In this example you have 100 closing prices for your given stock. Bar 1 is the oldest price, bar 100 is the most recent price. We will use a 20day regression.

1. Take prices 1-20 and draw the line of best fit through them
2. At the end of your best fit line (so bar 20), draw a little circle
3. Take prices 2-21 and draw the line of best fit through them
4. At the end of your best fit line (so bar 21) draw a little circle
5. Repeat upto bar 100
6. Join all of your little circles, this is your ‘linear regression curve’
So in a nutshell you just join the ends of a rolling linear regression.

Parameter Optimisation & Backtesting – Part 2

Posted on August 29, 2012 by GekkoQuant

This is a follow on from: http://gekkoquant.com/2012/08/29/parameter-optimisation-backtesting-part1/

The code presented here will aim to optimise a strategy based upon the simple moving average indicator. The strategy will go Long when moving average A > moving average B. The optimisation is to determine what period to make each of the moving averages A & B.

Please note that this isn’t intended to be a good strategy, it is merely here to give an example of how to optimise a parameter.

Onto the code:

Functions

TradingStrategy this function implements the trading logic and calculates the returns
RunIterativeStrategy this function iterates through possible parameter combinations and calls TradingStrategy for each new parameter set
CalculatePerformanceMetric takes in a table of returns (from RunIterativeStrategy) and runs a function/metric over each set of returns.
PerformanceTable calls CalculatePerformanceMetric for lots of different metric and compiles the results into a table
OrderPerformanceTable lets us order the performance table by a given metric, ie order by highest sharpe ratio
SelectTopNStrategies selects the best N strategies for a specified performance metric (charts.PerformanceSummary can only plot ~20 strategies, hence this function to select a sample)
FindOptimumStrategy does what it says on the tin

Note that when performing the out of sample test, you will need to manual specify the parameter set that you wish to use.

^?View Code RSPLUS

 
library("quantmod")
library("PerformanceAnalytics")
 
 
nameOfStrategy <- "GSPC Moving Average Strategy"
 
#Specify dates for downloading data, training models and running simulation
trainingStartDate = as.Date("2000-01-01")
trainingEndDate = as.Date("2010-01-01")
outofSampleStartDate = as.Date("2010-01-02")
 
 
#Download the data
symbolData <- new.env() #Make a new environment for quantmod to store data in
getSymbols("^GSPC", env = symbolData, src = "yahoo", from = trainingStartDate)
trainingData <- window(symbolData$GSPC, start = trainingStartDate, end = trainingEndDate)
testData <- window(symbolData$GSPC, start = outofSampleStartDate)
indexReturns <- Delt(Cl(window(symbolData$GSPC, start = outofSampleStartDate)))
colnames(indexReturns) <- "GSPC Buy&Hold"
 
TradingStrategy <- function(mktdata,mavga_period,mavgb_period){
  #This is where we define the trading strategy
  #Check moving averages at start of the day and use as the direciton signal
  #Enter trade at the start of the day and exit at the close
 
  #Lets print the name of whats running
  runName <- paste("MAVGa",mavga_period,".b",mavgb_period,sep="")
  print(paste("Running Strategy: ",runName))
 
  #Calculate the Open Close return
  returns <- (Cl(mktdata)/Op(mktdata))-1
 
  #Calculate the moving averages
  mavga <- SMA(Op(mktdata),n=mavga_period)
  mavgb <- SMA(Op(mktdata),n=mavgb_period)
 
  signal <- mavga / mavgb
  #If mavga > mavgb go long
  signal <- apply(signal,1,function (x) { if(is.na(x)){ return (0) } else { if(x>1){return (1)} else {return (-1)}}})
 
  tradingreturns <- signal * returns
  colnames(tradingreturns) <- runName
 
  return (tradingreturns)
}
 
RunIterativeStrategy <- function(mktdata){
  #This function will run the TradingStrategy
  #It will iterate over a given set of input variables
  #In this case we try lots of different periods for the moving average
  firstRun <- TRUE
    for(a in 1:10) {
        for(b in 1:10) {
 
          runResult <- TradingStrategy(mktdata,a,b)
 
          if(firstRun){
              firstRun <- FALSE
              results <- runResult
          } else {
              results <- cbind(results,runResult)
          }
        }
    }
 
   return(results)
}
 
CalculatePerformanceMetric <- function(returns,metric){
  #Get given some returns in columns
  #Apply the function metric to the data
 
  print (paste("Calculating Performance Metric:",metric))
 
  metricFunction <- match.fun(metric)
  metricData <- as.matrix(metricFunction(returns))
  #Some functions return the data the wrong way round
  #Hence cant label columns to need to check and transpose it
  if(nrow(metricData) == 1){
    metricData <- t(metricData)
  }
  colnames(metricData) <- metric
 
  return (metricData)
}
 
 
 
PerformanceTable <- function(returns){
  pMetric <- CalculatePerformanceMetric(returns,"colSums")
  pMetric <- cbind(pMetric,CalculatePerformanceMetric(returns,"SharpeRatio.annualized"))
  pMetric <- cbind(pMetric,CalculatePerformanceMetric(returns,"maxDrawdown"))
  colnames(pMetric) <- c("Profit","SharpeRatio","MaxDrawDown")
 
  print("Performance Table")
  print(pMetric)
  return (pMetric)
}
 
OrderPerformanceTable <- function(performanceTable,metric){
return (performanceTable[order(performanceTable[,metric],decreasing=TRUE),])
}
 
SelectTopNStrategies <- function(returns,performanceTable,metric,n){
#Metric is the name of the function to apply to the column to select the Top N
#n is the number of strategies to select
  pTab <- OrderPerformanceTable(performanceTable,metric)
 
  if(n > ncol(returns)){
     n <- ncol(returns)
  }
  strategyNames <- rownames(pTab)[1:n]
  topNMetrics <- returns[,strategyNames]
  return (topNMetrics)
}
 
FindOptimumStrategy <- function(trainingData){
  #Optimise the strategy
  trainingReturns <- RunIterativeStrategy(trainingData)
  pTab <- PerformanceTable(trainingReturns)
  toptrainingReturns <- SelectTopNStrategies(trainingReturns,pTab,"SharpeRatio",5)
  charts.PerformanceSummary(toptrainingReturns,main=paste(nameOfStrategy,"- Training"),geometric=FALSE)
  return (pTab)
}
 
pTab <- FindOptimumStrategy(trainingData) #pTab is the performance table of the various parameters tested
 
#Test out of sample
dev.new()
#Manually specify the parameter that we want to trade here, just because a strategy is at the top of
#pTab it might not be good (maybe due to overfit)
outOfSampleReturns <- TradingStrategy(testData,mavga_period=9,mavgb_period=6)
finalReturns <- cbind(outOfSampleReturns,indexReturns)
charts.PerformanceSummary(finalReturns,main=paste(nameOfStrategy,"- Out of Sample"),geometric=FALSE)

Trading Strategy – VWAP Mean Reversion

Posted on July 31, 2012 by GekkoQuant

This strategy is going to use the volume weighted average price (VWAP) as an indicator to trade mean version back to VWAP. Annualized Sharpe Ratio (Rf=0%) is 0.9016936.

This post is a response to http://gekkoquant.com/2012/07/29/trading-strategy-sp-vwap-trend-follow/ where there was a bug in the code indicating that VWAP wasn’t reverting (this didn’t sit well with me, or some of the people who commented). As always don’t take my word for anything, backtest the strategy yourself. One of the dangers of using R or Matlab is that it’s easy for forward bias to slip into your code. There are libraries such as Quantstrat for R which protect against this, but I’ve found them terribly slow to run.

Trade logic:

All conditions are checked at the close, and the trade held for one day from the close
If price/vwap > uLim go short
If price/vwap < lLim go long

Onto the code:

^?View Code RSPLUS

library("quantmod")
library("PerformanceAnalytics")
 
#Trade logic - Look for mean reversion
#If price/vwap > uLim go SHORT
#If price/vwap < lLim go LONG
 
#Script parameters
symbol <- "^GSPC"     #Symbol
nlookback <- 3 #Number of days to lookback and calculate vwap
uLim <- 1.001  #If price/vwap > uLim enter a short trade
lLim <- 0.999  #If price/vwap < lLim enter a long trade
 
 
#Specify dates for downloading data
startDate = as.Date("2006-01-01") #Specify what date to get the prices from
symbolData <- new.env() #Make a new environment for quantmod to store data in
getSymbols(symbol, env = symbolData, src = "yahoo", from = startDate)
mktdata <- eval(parse(text=paste("symbolData$",sub("^","",symbol,fixed=TRUE))))
mktdata <- head(mktdata,-1) #Hack to fix some stupid duplicate date problem with yahoo
 
#Calculate volume weighted average price
vwap <- VWAP(Cl(mktdata), Vo(mktdata), n=nlookback)
#Can calculate vwap like this, but it is slower
#vwap <- runSum(Cl(mktdata)*Vo(mktdata),nlookback)/runSum(Vo(mktdata),nlookback)
 
#Calulate the daily returns
dailyRet <- Delt(Cl(mktdata),k=1,type="arithmetic") #Daily Returns
 
#signal = price/vwap
signal <- Cl(mktdata) / vwap
signal[is.na(signal)] <- 1 #Setting to one means that no trade will occur for NA's
#Stripping NA's caused all manner of problems in a previous post
trade <- apply(signal,1, function(x) {if(x<lLim) { return (1) } else { if(x>uLim) { return(-1) } else { return (0) }}})
 
#Calculate the P&L
#The daily ret is DailyRet(T)=(Close(T)-Close(T-1))/Close(T-1)
#We enter the trade on day T so need the DailyRet(T+1) as our potential profit
#Hence the lag in the line below
strategyReturns <- trade * lag(dailyRet,-1)
strategyReturns <- na.omit(strategyReturns)
 
#### Performance Analysis ###
#Calculate returns for the index
indexRet <- dailyRet #Daily returns
colnames(indexRet) <- "IndexRet"
zooTradeVec <- cbind(as.zoo(strategyReturns),as.zoo(indexRet)) #Convert to zoo object
colnames(zooTradeVec) <- c(paste(symbol," VWAP Trade"),symbol)
zooTradeVec <- na.omit(zooTradeVec)
 
#Lets see how all the strategies faired against the index
dev.new()
charts.PerformanceSummary(zooTradeVec,main=paste("Performance of ", symbol, " VWAP Strategy"),geometric=FALSE)
 
 
#Lets calculate a table of montly returns by year and strategy
cat("Calander Returns - Note 13.5 means a return of 13.5%\n")
print(table.CalendarReturns(zooTradeVec))
#Calculate the sharpe ratio
cat("Sharpe Ratio")
print(SharpeRatio.annualized(zooTradeVec))

Trading Strategy – S&P VWAP Trend Follow (BUGGY)

Posted on July 29, 2012 by GekkoQuant

UPDATE: The exceptional returns seen in this strategy were due to a 2 day look forward bias in the signal (and then subsequent trade direction), ie when returns were calculated for day T the trade signal used was actually from day T+2.

This bias occurred in the lines:

^?View Code RSCODE

signal <- na.omit(signal)

Both the signal and trade dataframe had the correct dates for each signal/trades however when indexRet*trade happened then trade was treated as undated vectors (which is 2 elements shorter than index ret) hence the 2 day shift. The moral of this story is to merge dataframes before multiplying!

Thank you for everyone that commented on this, a corrected post is to follow!

Original Post

This strategy is going to use the volume weighted average price (VWAP) as an indicator to determine the direction of the current trend and trade the same direction as the trend. Annualized Sharpe Ratio (Rf=0%) is 8.510472.

Trade logic:

All conditions are checked at the close, and the trade held for one day from the close
If price/vwap > uLim go long
If price/vwap < lLim go short

Initially I thought that the price would be mean reverting to VWAP (this can be see in high freq data) however this didn’t appear to be the case with EOD data. For such a simple strategy I’m amazed that the Sharpe ratio is so high (suspiciously high). The code has been double&tripple checked to see if any forward bias has slipped in, however I haven’t spotted anything.

Onto the code:

^?View Code RSPLUS

library("quantmod")
library("PerformanceAnalytics")
 
#Trade logic - Follow the trade demand, ie if price > vwap then go long
#If price/vwap > uLim go LONG
#If price/vwap < lLim go SHORT
 
#Script parameters
symbol <- "^GSPC"     #Symbol
nlookback <- 3 #Number of days to lookback and calculate vwap
uLim <- 1.001  #If price/vwap > uLim enter a long trade
lLim <- 0.999  #If price/vwap < lLim enter a short trade
 
 
#Specify dates for downloading data
startDate = as.Date("2006-01-01") #Specify what date to get the prices from
symbolData <- new.env() #Make a new environment for quantmod to store data in
getSymbols(symbol, env = symbolData, src = "yahoo", from = startDate)
mktdata <- eval(parse(text=paste("symbolData$",sub("^","",symbol,fixed=TRUE))))
mktdata <- head(mktdata,-1) #Hack to fix some stupid duplicate date problem with yahoo
 
#Calculate volume weighted average price
vwap <- VWAP(Cl(mktdata), Vo(mktdata), n=nlookback)
#Can calculate vwap like this, but it is slower
#vwap <- runSum(Cl(mktdata)*Vo(mktdata),nlookback)/runSum(Vo(mktdata),nlookback)
 
#Calulate the daily returns
dailyRet <- Delt(Cl(mktdata),k=1,type="arithmetic") #Daily Returns
 
#signal = price/vwap
signal <- Cl(mktdata) / vwap
signal <- na.omit(signal)
trade <- apply(signal,1, function(x) {if(x<lLim) { return (-1) } else { if(x>uLim) { return(1) } else { return (0) }}})
 
#Calculate the P&L
#The daily ret is DailyRet(T)=(Close(T)-Close(T-1))/Close(T-1)
#We enter the trade on day T so need the DailyRet(T+1) as our potential profit
#Hence the lag in the line below
strategyReturns <- trade * lag(dailyRet,-1)
strategyReturns <- na.omit(strategyReturns)
 
#### Performance Analysis ###
#Calculate returns for the index
indexRet <- dailyRet #Daily returns
colnames(indexRet) <- "IndexRet"
zooTradeVec <- cbind(as.zoo(strategyReturns),as.zoo(indexRet)) #Convert to zoo object
colnames(zooTradeVec) <- c(paste(symbol," VWAP Trade"),symbol)
zooTradeVec <- na.omit(zooTradeVec)
 
#Lets see how all the strategies faired against the index
dev.new()
charts.PerformanceSummary(zooTradeVec,main=paste("Performance of ", symbol, " VWAP Strategy"),geometric=FALSE)
 
 
#Lets calculate a table of montly returns by year and strategy
cat("Calander Returns - Note 13.5 means a return of 13.5%\n")
print(table.CalendarReturns(zooTradeVec))
#Calculate the sharpe ratio
cat("Sharpe Ratio")
print(SharpeRatio.annualized(zooTradeVec))

Trading Strategy – Volatility Carry Trade

Posted on June 24, 2012 by GekkoQuant

This strategy is going to look at a vega neutral volatility carry trading strategy. Two different futures contract will be traded, the VXX and VXZ. These contracts are rolling futures on the S&P 500 Vix index, the VXX is a short term future and the VXZ is a medium term future. Annualized Sharpe Ratio (Rf=0%) is 1.759449.

The strategy is very simple, the rules are:

If VXX / VXZ > 1 then in backwardation so do a reverse carry trade (buy VXX, sell VXZ)
If VXX / VXZ < 1 then do a carry trade (sell VXX, buy VXZ)

If the volatility spot price doesn’t change, then we’re extracting the cost of carry. Due to buying and selling (or vice versa) the short to mid term futures the vega exposure is hedged.

In the script the above two rules have been slightly changed, a slight offset is added/subtracted from the ratio. Essentially we want to be deep into contango zone or deep into backwardation zone before we trade, if we’re close to the flip point then don’t trade.

Section 1: Downloaded the data, and calculate the Open to Close return. This strategy will look for entry at the open and exit at the close.

Section 2: Regress the daily returns of VXX with VXZ to calculate the hedge ratio

Section 3: Generate the backwardation / contango signal

Section 4: Simulate the trading

Section 5: Analyse the performance

Onto the code:

^?View Code RSPLUS

library("quantmod")
library("PerformanceAnalytics")
 
#Control variables for entering a trade
#Used to check for the level of contango / backwardation
#IF signal < signalLowLim then in contango and do a carry trade
#IF signal > signalUpperLim then in backwardation so do a reverse carry
#ELSE do nothing
signalLowLim <- 0.9
signalUpperLim <- 1.1
 
#Use volatility futures, shortdate vs medium dated
#VXX iPath S&P 500 VIX Short-Term Futures ETN (VXX)
#VXZ iPath S&P 500 VIX Mid-Term Futures ETN (VXZ)
symbolLst <- c("VXX","VXZ")
 
#Specify dates for downloading data, training models and running simulation
startDate = as.Date("2009-01-01") #Specify what date to get the prices from
hedgeTrainingStartDate = as.Date("2009-01-01") #Start date for training the hedge ratio
hedgeTrainingEndDate = as.Date("2009-05-01") #End date for training the hedge ratio
tradingStartDate = as.Date("2009-05-02") #Date to run the strategy from
 
### SECTION 1 - Download Data & Calculate Returns ###
#Download the data
symbolData <- new.env() #Make a new environment for quantmod to store data in
getSymbols(symbolLst, env = symbolData, src = "yahoo", from = startDate)
 
#Plan is to check for trade entry at the open, and exit the trade at the close
#So need to calculate the open to close return as they represens our profit or loss
#Calculate returns for VXX and VXZ
vxxRet <- (Cl(symbolData$VXX)/Op(symbolData$VXX))-1
colnames(vxxRet) <- "Ret"
symbolData$VXX <- cbind(symbolData$VXX,vxxRet)
 
vxzRet <- (Cl(symbolData$VXZ)/Op(symbolData$VXZ))-1
colnames(vxzRet) <- "Ret"
symbolData$VXZ <- cbind(symbolData$VXZ,vxzRet)
 
### SECTION 2 - Calculating the hedge ratio ###
#Want to work out a hedge ratio, so that we can remain Vega neutral (the futures contact are trading VEGA)
#Select a small amount of data for training the hedge model on
subVxx <- window(symbolData$VXX$Ret,start=hedgeTrainingStartDate ,end=hedgeTrainingEndDate)
subVxz <- window(symbolData$VXZ$Ret,start=hedgeTrainingStartDate ,end=hedgeTrainingEndDate)
datablock = na.omit(cbind(subVxx,subVxz))
colnames(datablock) <- c("VXX","VXZ")
 
#Simply linearly regress the returns of Vxx with Vxz
regression <- lm(datablock[,"VXZ"] ~ datablock[,"VXX"]) #Linear Regression
 
#Plot the regression
plot(x=as.vector(datablock[,"VXX"]), y=as.vector(datablock[,"VXZ"]), main=paste("Hedge Regression: XXZret =",regression$coefficient[2]," * RXXret + intercept"),
  	 xlab="Vxx Ret", ylab="Vxz ", pch=19)
abline(regression, col = 2 )
hedgeratio = regression$coefficient[2]
 
 
### SECTION 3 - Generate trading signals ###
#Generate Trading signal
#Check ratio to see if contango or backwarded volatility future
#If shortTermVega < midTermVega in contango so do carry trade
#If shortTermVega > midTermVega in backwardation so do reverse carry
#If VXX less than VXZ then want to short VXX and long VXZ
 
#Calculate the contango / backwardation signal
tSig <- Op(symbolData$VXX)/Op(symbolData$VXZ)
colnames(tSig) <- "Signal"
 
### SECTION 4 - Do the trading ###
#Generate the individual buy/sell signals for each of the futures contract
vxxSignal <- apply(tSig,1, function(x) {if(x<signalLowLim) { return (-1) } else { if(x>signalUpperLim) { return(1) } else { return (0) }}})
vxzSignal <- -1 * vxxSignal
 
#Strategy returns are simply the direction * the Open-to-Close return for the day
#Include the hedge ratio here so that we remain vega neutral
strategyReturns <- ((vxxSignal * symbolData$VXX$Ret) + hedgeratio * (vxzSignal * symbolData$VXZ$Ret) )
strategyReturns <- window(strategyReturns,start=tradingStartDate,end=Sys.Date(), extend = FALSE)
#Normalise the amount of money being invested on each trade so that we can compare to the S&P index later
strategyReturns <- strategyReturns * 1 / (1+abs(hedgeratio))
colnames(strategyReturns) <- "StrategyReturns"
#plot(cumsum(strategyReturns))
 
#SECTION 5
#### Performance Analysis ###
 
#Get the S&P 500 index data
indexData <- new.env()
startDate = as.Date("2009-01-01") #Specify what date to get the prices from
getSymbols("^GSPC", env = indexData, src = "yahoo", from = startDate)
 
#Calculate returns for the index
indexRet <- (Cl(indexData$GSPC)-lag(Cl(indexData$GSPC),1))/lag(Cl(indexData$GSPC),1)
colnames(indexRet) <- "IndexRet"
zooTradeVec <- cbind(as.zoo(strategyReturns),as.zoo(indexRet)) #Convert to zoo object
colnames(zooTradeVec) <- c("Vol Carry Trade","S&P500")
zooTradeVec <- na.omit(zooTradeVec)
#Lets see how all the strategies faired against the index
dev.new()
charts.PerformanceSummary(zooTradeVec,main="Performance of Volatility Carry Trade",geometric=FALSE)
 
#Lets calculate a table of montly returns by year and strategy
cat("Calander Returns - Note 13.5 means a return of 13.5%\n")
print(table.CalendarReturns(zooTradeVec))
#Calculate the sharpe ratio
cat("Sharpe Ratio")
print(SharpeRatio.annualized(zooTradeVec))
#Calculate other statistics
cat("Other Statistics")
print(table.CAPM(zooTradeVec[,"Vol Carry Trade"],zooTradeVec[,"S&P500"]))
 
dev.new()
#Lets make a boxplot of the returns
chart.Boxplot(zooTradeVec)
 
dev.new()
#Set the plotting area to a 2 by 2 grid
layout(rbind(c(1,2),c(3,4)))
 
#Plot various histograms with different overlays added
chart.Histogram(zooTradeVec, main = "Plain", methods = NULL)
chart.Histogram(zooTradeVec, main = "Density", breaks=40, methods = c("add.density", "add.normal"))
chart.Histogram(zooTradeVec, main = "Skew and Kurt", methods = c("add.centered", "add.rug"))
chart.Histogram(zooTradeVec, main = "Risk Measures", methods = c("add.risk"))

Trading Strategy – Buy on Gap (EPChan)

Posted on June 1, 2012 by GekkoQuant

This post is going to investigate a strategy called Buy on Gap that was discussed by E.P Chan in his blog post “the life and death of a strategy”. The strategy is a mean reverting strategy that looks to buy the weakest stocks in the S&P 500 at the open and liquidate the positions at the close. The performance of the strategy is seen in the image below, Annualized Sharpe Ratio (Rf=0%) 2.129124.

All numbers in this table are %(ie 12.6 is 12.6%)
      Jan  Feb  Mar  Apr  May  Jun  Jul  Aug  Sep  Oct  Nov  Dec BuyOnGap S&P500
2005  0.0  0.0  0.0  0.0  0.0 -0.4 -0.6  1.1  0.7  1.0 -0.2  0.3      1.8   -0.1
2006  0.2 -0.6 -0.3  0.0  1.1  0.1  0.0  0.4  0.1  0.1  0.2 -0.2      1.1   -2.0
2007  0.8  0.9  0.1 -1.1  0.3 -0.2 -1.5  0.2 -0.2  0.9 -0.4  0.3      0.0    1.0
2008  4.3 -1.9  0.8 -0.5  0.0  0.7  0.2 -0.7  2.0  3.3  2.0  2.0     12.6    6.0
2009 -2.9  0.1  1.4 -1.1  1.3 -0.8  0.4  0.0 -0.3 -1.9  0.8 -1.0     -4.0   -7.3
2010 -1.0 -0.1  0.0 -1.1 -0.7 -0.6  1.1  0.7 -0.5  0.6  0.5  0.1     -1.1   -5.9
2011  0.6  0.3  0.2 -0.1  0.2  0.4  0.7  0.1 -1.4 -1.2  1.4 -0.2      1.0    2.1
2012 -0.3 -0.5 -0.1  0.0 -1.0   NA   NA   NA   NA   NA   NA   NA     -1.8   -0.8

From the post two trading criterion were mentioned:

Buy the 100 stocks out of the S&P 500 constituents that have the lowest previous days lows to the current days opening price
Provided that the above return is less than the 1 times the 90day standard deviation of Close to Close returns

The criterion are fairly specific however it is important to write flexible code where it is easy to change the main model parameters, below is a list of variable names that specify the parameters in the R script:

nStocksBuy – How many stocks to buy
stdLookback – How many days to look back for the standard deviation calculation
stdMultiple – Number to multiply the standard deviation by (was 1 in criterion 2.), the larger this variable the more stocks that will satisfy criterion 2.

The code is split into 5 distinct sections.

Section 1: Loop through all the stocks loaded from the data file, for each stock calculate the previous day close to current days open (lowOpenRet). Calculate the Close Close return and calculate the standard deviation (stdClClRet). Also calculate the Open to Close return for every day (dayClOpRet), if we decide to trade this day this would be the return of the strategy for the day.

Section 2: This section combines columns from each of the individual stock data frames into large matrices that cover all the stocks. retMat contains the lowOpenRet for each stock. stdMat contains the stdClClRet for all stocks, dayretMat contains the dayClOpRet for all stocks.

Essentially instead of having lots of variables, we combine them into a big matrix.

Section 3: This will check if matrices in section 2 match the trade entry criterion. This section produces two matrices (conditionOne and conditionTwo). The matrices contain a 1 for a passed entry criterion and a 0 for a failed entry criterion.

Section 4: This multiples the conditionOne with conditionTwo to give conditionsMet, since those matricies are binary multiplying them together identifies the regions where both conditions passed (1*1=1 ie a pass). This means enter a trade.

conditionsMet is then used as a mask, it has 1′s when a trade should occur and 0′s when no trade should happen. So multiplying this with dayClOpRet gives us the Open to Close daily returns for all days and stocks that a trade occurred on.

The script assumes capital is split equally between all the stocks that are bought at the open, if less than 100 stocks meet the entry criteria then it is acceptable to buy less.

Section 5: This section does simple performance analytics and plots the equity curve against the S&P 500 index.

Onto the code (note the datafile is generated in Stock Data Download & Saving R):

^?View Code RSPLUS

#install.packages("quantmod")
library("quantmod")
#install.packages("caTools") #for rolling standard deviation
library("caTools")
#install.packages("PerformanceAnalytics")
library("PerformanceAnalytics") #Load the PerformanceAnalytics library
 
datafilename = "stockdata.RData"
 
stdLookback <- 90 #How many periods to lookback for the standard deviation calculation
stdMultiple <- 1 #A Number to multiply the standard deviation by
nStocksBuy <- 100 #How many stocks to buy
 
load(datafilename)
 
#CONDITION 1
#Buy 100 stocks with lowest returns from their previous days lows
#To the current days open
 
#CONDITION 2
#Provided returns are lower than one standard deviation of the
#90 day moving standard deviation of close close returns
#Exit long positions at the end of the day
 
 
#SECTION 1
symbolsLst <- ls(stockData)
#Loop through all stocks in stockData and calculate required returns / stdev's
for (i in 1:length(symbolsLst)) {
cat("Calculating the returns and standard deviations for stock: ",symbolsLst[i],"\n")
sData <- eval(parse(text=paste("stockData$",symbolsLst[i],sep="")))
#Rename the colums, there is a bug in quantmod if a stock is called Low then Lo() breaks!
#Ie if a column is LOW.x then Lo() breaks
oldColNames <- names(sData)
colnames(sData) <- c("S.Open","S.High","S.Low","S.Close","S.Volume","S.Adjusted")
 
#Calculate the return from low of yesterday to the open of today
lowOpenRet <- (Op(sData)-lag(Lo(sData),1))/lag(Lo(sData),1)
colnames(lowOpenRet) <- paste(symbolsLst[i],".LowOpenRet",sep="")
 
#Calculate the n day standard deviation from the close of yesterday to close 2 days ago
stdClClRet <- runsd((lag(Cl(sData),1)-lag(Cl(sData),2))/lag(Cl(sData),2),k=stdLookback,endrule="NA",align="right")
stdClClRet <- stdMultiple*stdClClRet + runmean(lag(Cl(sData),1)/lag(Cl(sData),2),k=stdLookback,endrule="NA",align="right")
colnames(stdClClRet) <- paste(symbolsLst[i],".StdClClRet",sep="")
 
#Not part of the strategy but want to calculate the Close/Open ret for current day
#Will use this later to evaluate performance if a trade was taken
dayClOpRet <- (Cl(sData)-Op(sData))/Op(sData)
colnames(dayClOpRet) <- paste(symbolsLst[i],".DayClOpRet",sep="")
 
colnames(sData) <- oldColNames
eval(parse(text=paste("stockData$",symbolsLst[i]," <- cbind(sData,lowOpenRet,stdClClRet,dayClOpRet)",sep="")))
}
 
#SECTION 2
#Have calculated the relevent returns and standard deviations
#Now need to to work out what 100 (nStocksBuy) stocks have the lowest returns
#Make a returns matrix
for (i in 1:length(symbolsLst)) {
  cat("Assing stock: ",symbolsLst[i]," to the returns table\n")
  sDataRET <- eval(parse(text=paste("stockData$",symbolsLst[i],"[,\"",symbolsLst[i],".LowOpenRet\"]",sep="")))
  sDataSTD <- eval(parse(text=paste("stockData$",symbolsLst[i],"[,\"",symbolsLst[i],".StdClClRet\"]",sep="")))
  sDataDAYRET <- eval(parse(text=paste("stockData$",symbolsLst[i],"[,\"",symbolsLst[i],".DayClOpRet\"]",sep="")))
  if(i == 1){
  retMat <- sDataRET
  stdMat <- sDataSTD
  dayretMat <- sDataDAYRET
  } else {
  retMat <- cbind(retMat,sDataRET)
  stdMat <- cbind(stdMat,sDataSTD)
  dayretMat <- cbind(dayretMat,sDataDAYRET)
  }
}
 
#SECTION 3
#CONDITON 1 test output (0 = failed test, 1 = passed test)
#Now will loop over the returns matrix finding the nStocksBuy smallest returns
conditionOne <- retMat #copying the structure and data, only really want the structure
conditionOne[,] <- 0 #set all the values to 0
for (i in 1:length(retMat[,1])){
orderindex <- order((retMat[i,]),decreasing=FALSE)  #order row entries smallest to largest
orderindex <- orderindex[1:nStocksBuy] #want the smallest n (nStocksBuy) stocks
conditionOne[i,orderindex] <- 1 #1 Flag indicates entry is one of the nth smallest
}
 
#CONDITON 2
#Check Close to Open return is less than 90day standard deviation
conditionTwo <- retMat #copying the structure and data, only really want the structure
conditionTwo[,] <- 0 #set all the values to 0
conditionTwo <- retMat/stdMat #If ClOp ret is < StdRet tmp will be < 1
conditionTwo[is.na(conditionTwo)] <- 2 #GIVE IT FAIL CONDITION JUST STRIPPING NAs here
conditionTwo <- apply(conditionTwo,1:2, function(x) {if(x<1) { return (1) } else { return (0) }})
 
#SECTION 4
#CHECK FOR TRADE output (1 = passed conditions for trade, 0 = failed test)
#Can just multiply the two conditions together since they're boolean
conditionsMet <- conditionOne * conditionTwo
colnames(conditionsMet) <- gsub(".LowOpenRet","",names(conditionsMet))
 
#Lets calculate the results
tradeMat <- dayretMat
colnames(tradeMat) <- gsub(".DayClOpRet","",names(tradeMat))
tradeMat <- tradeMat * conditionsMet
tradeMat[is.na(tradeMat)] <- 0
tradeVec <- as.data.frame(apply(tradeMat, 1,sum) / apply(conditionsMet, 1,sum)) #Calculate the mean for each row
colnames(tradeVec) <- "DailyReturns"
tradeVec[is.nan(tradeVec[,1]),1] <- 0 #Didnt make or loose anything on this day
 
plot(cumsum(tradeVec[,1]),xlab="Date", ylab="EPCHAN Buy on Gap",xaxt = "n")
 
#SECTION 5
#### Performance Analysis ###
 
#Get the S&P 500 index data
indexData <- new.env()
startDate = as.Date("2005-01-13") #Specify what date to get the prices from
getSymbols("^GSPC", env = indexData, src = "yahoo", from = startDate)
 
#Calculate returns for the index
indexRet <- (Cl(indexData$GSPC)-lag(Cl(indexData$GSPC),1))/lag(Cl(indexData$GSPC),1)
colnames(indexRet) <- "IndexRet"
zooTradeVec <- cbind(as.zoo(tradeVec),as.zoo(indexRet)) #Convert to zoo object
colnames(zooTradeVec) <- c("BuyOnGap","S&P500")
 
#Lets see how all the strategies faired against the index
dev.new()
charts.PerformanceSummary(zooTradeVec,main="Performance of EPCHAN Buy on Gap",geometric=FALSE)
 
#Lets calculate a table of montly returns by year and strategy
cat("Calander Returns - Note 13.5 means a return of 13.5%\n")
table.CalendarReturns(zooTradeVec)
 
dev.new()
#Lets make a boxplot of the returns
chart.Boxplot(zooTradeVec)
 
dev.new()
#Set the plotting area to a 2 by 2 grid
layout(rbind(c(1,2),c(3,4)))
 
#Plot various histograms with different overlays added
chart.Histogram(zooTradeVec, main = "Plain", methods = NULL)
chart.Histogram(zooTradeVec, main = "Density", breaks=40, methods = c("add.density", "add.normal"))
chart.Histogram(zooTradeVec, main = "Skew and Kurt", methods = c("add.centered", "add.rug"))
chart.Histogram(zooTradeVec, main = "Risk Measures", methods = c("add.risk"))

Possible Future Modifications

Add shorting the strongest stocks so that the strategy is market neutral
Vary how many stocks to hold
Vary the input variables (discussed above)
Try a different asset class, does this work for forex?

Stock Data Download & Saving R

Posted on June 1, 2012 by GekkoQuant

The quantmod library will be used to download prices from yahoo. This script allows a csv of tickers to be loaded and automatically downloaded. The script also has primitive error handling and is capable of retrying the download of the price history for a stock. Sometimes yahoo randomly returns error 404 for stock downloads, this script will retry a couple of times using getting around this problem.

Any data downloaded will be saved to a RData file, this allows the data to be analysed by another script. Rather than having each trading strategy maintaining its own stock data it is preferential to have one script (this one) to download the data which can then be shared across strategies.

From now on the strategies examined on this site will their price data from the output of this script.

Attached is a list of sp500 tickers (taken from the brilliant blog.quanttrader.org)

Onto the code:

^?View Code RSPLUS

#install.packages("quantmod")
library("quantmod")
#Script to download prices from yahoo
#and Save the prices to a RData file
#The tickers will be loaded from a csv file
 
#Script Parameters
tickerlist <- "sp500.csv"  #CSV containing tickers on rows
savefilename <- "stockdata.RData" #The file to save the data in
startDate = as.Date("2005-01-13") #Specify what date to get the prices from
maxretryattempts <- 5 #If there is an error downloading a price how many times to retry
 
#Load the list of ticker symbols from a csv, each row contains a ticker
stocksLst <- read.csv("sp500.csv", header = F, stringsAsFactors = F)
stockData <- new.env() #Make a new environment for quantmod to store data in
nrstocks = length(stocksLst[,1]) #The number of stocks to download
 
#Download all the stock data
for (i in 1:nrstocks){
    for(t in 1:maxretryattempts){
 
       tryCatch(
           {
               #This is the statement to Try
               #Check to see if the variables exists
               #NEAT TRICK ON HOW TO TURN A STRING INTO A VARIABLE
               #SEE  http://www.r-bloggers.com/converting-a-string-to-a-variable-name-on-the-fly-and-vice-versa-in-r/
                if(!is.null(eval(parse(text=paste("stockData$",stocksLst[i,1],sep=""))))){
                    #The variable exists so dont need to download data for this stock
                    #So lets break out of the retry loop and process the next stock
                    #cat("No need to retry")
                    break
                }
 
              #The stock wasnt previously downloaded so lets attempt to download it
              cat("(",i,"/",nrstocks,") ","Downloading ", stocksLst[i,1] , "\t\t Attempt: ", t , "/", maxretryattempts,"\n")
              getSymbols(stocksLst[i,1], env = stockData, src = "yahoo", from = startDate)
           }
        #Specify the catch function, and the finally function
       , error = function(e) print(e))
     }
}
 
#Lets save the stock data to a data file
tryCatch(
    {
    save(stockData, file=savefilename)
    cat("Sucessfully saved the stock data to %s",savefilename)
    }
    , error = function(e) print(e))

Neural Networks with R – A Simple Example

Posted on May 26, 2012 by GekkoQuant

In this tutorial a neural network (or Multilayer perceptron depending on naming convention) will be build that is able to take a number and calculate the square root (or as close to as possible). Later tutorials will build upon this to make forcasting / trading models.The R library ‘neuralnet’ will be used to train and build the neural network.

There is lots of good literature on neural networks freely available on the internet, a good starting point is the neural network handout by Dr Mark Gayles at the Engineering Department Cambridge University http://mi.eng.cam.ac.uk/~mjfg/local/I10/i10_hand4.pdf, it covers just enough to get an understanding of what a neural network is and what it can do without being too mathematically advanced to overwhelm the reader.

The tutorial will produce the neural network shown in the image below. It is going to take a single input (the number that you want square rooting) and produce a single output (the square root of the input). The middle of the image contains 10 hidden neurons which will be trained.

The output of the script will look like:

Input Expected Output Neural Net Output

   Input 	Expected Output		 Neural Net Output
      1               1     		 0.9623402772
      4               2     		 2.0083461217
      9               3     		 2.9958221776
     16               4     		 4.0009548085
     25               5     		 5.0028838579
     36               6     		 5.9975810435
     49               7    		 6.9968278722
     64               8    		 8.0070028670
     81               9    		 9.0019220736
    100              10    		 9.9222007864

As you can see the neural network does a reasonable job at finding the square root, the largest error in in finding the square root of 1 which is out by ~4%

Onto the code:

^?View Code RSPLUS

install.packages('neuralnet')
library("neuralnet")
 
#Going to create a neural network to perform sqare rooting
#Type ?neuralnet for more information on the neuralnet library
 
#Generate 50 random numbers uniformly distributed between 0 and 100
#And store them as a dataframe
traininginput <-  as.data.frame(runif(50, min=0, max=100))
trainingoutput <- sqrt(traininginput)
 
#Column bind the data into one variable
trainingdata <- cbind(traininginput,trainingoutput)
colnames(trainingdata) <- c("Input","Output")
 
#Train the neural network
#Going to have 10 hidden layers
#Threshold is a numeric value specifying the threshold for the partial
#derivatives of the error function as stopping criteria.
net.sqrt <- neuralnet(Output~Input,trainingdata, hidden=10, threshold=0.01)
print(net.sqrt)
 
#Plot the neural network
plot(net.sqrt)
 
#Test the neural network on some training data
testdata <- as.data.frame((1:10)^2) #Generate some squared numbers
net.results <- compute(net.sqrt, testdata) #Run them through the neural network
 
#Lets see what properties net.sqrt has
ls(net.results)
 
#Lets see the results
print(net.results$net.result)
 
#Lets display a better version of the results
cleanoutput <- cbind(testdata,sqrt(testdata),
                         as.data.frame(net.results$net.result))
colnames(cleanoutput) <- c("Input","Expected Output","Neural Net Output")
print(cleanoutput)

PerformanceAnalytics Basics – Measure Strategy Performance and Risk

Posted on May 14, 2012 by GekkoQuant

In this quick tutorial I will introduce the PerformanceAnalytics library, the library lets us easily analyse the performance of our strategies. In this tutorial you will learn how to plot cumulative returns and draw downs compared to an index, output a table of monthly performance metrics, use boxplots to investigate strategy outliers and finally plot histograms of returns and overlay with different statistical measures.

You will need some returns data for this tutorial, I have created a file with some returns in to get you started: strategyperfomance.csv

The three image outputs are:

The text output is:


      Jan  Feb  Mar  Apr  May  Jun  Jul  Aug  Sep  Oct  Nov  Dec Strategy1 Strategy2 Index
2005  1.8  0.0 -0.3  1.9  1.4  1.4  0.7  1.3  0.7  0.0  1.2  1.2      12.0       9.2   9.6
2006  0.1  0.9  0.9  1.4  1.0  1.8 -1.7  0.4  1.0  0.2  0.1  0.5       6.9       4.0   6.3
2007  1.5  0.5  0.4 -0.9  1.3  1.8 -2.9 -0.3 -0.2 -1.1 -1.3  0.5      -0.9      -4.5  -3.7
2008  1.8 -1.0  3.5  1.5  0.2 -2.4 -1.0 -1.3  1.3  2.1 -5.3  2.9       1.9       0.4  -0.9
2009 -2.0 -4.4  0.5 -0.5  2.4  3.1  2.0 -0.6 -1.9  1.6  2.2  1.7       3.8      -0.5   0.8
2010  1.4  1.1 -0.8 -3.0 -0.1 -3.3  2.6  4.1  1.4  0.2  2.8  1.5       8.0       8.3   8.6
2011  0.9 -0.2  0.7  1.0 -1.3  2.5  0.6  0.5 -0.5 -2.0 -0.5 -0.6       1.0      -1.2  -1.5

Onto the code:

^?View Code RSPLUS

install.packages("PerformanceAnalytics") #Install the PerformanceAnalytics library
library("PerformanceAnalytics") #Load the PerformanceAnalytics library
 
#Load in our strategy performance spreadsheet
#Structure is: Date,Strategy1,Strategy2,Index
#Each row contains the period returns (% terms)
 
strategies <- read.zoo("strategyperfomance.csv", sep = ",", header = TRUE, format="%Y-%m-%d")
head(strategies)
 
#List all the column names to check data loaded in correctly
#Can access colums with strategies["columnname"]
colnames(strategies)
 
#Lets see how all the strategies faired against the index
charts.PerformanceSummary(strategies,main="Performance of all Strategies")
 
#Lets see how just strategy one faired against the index
charts.PerformanceSummary(strategies[,c("Strategy1","Index")],main="Performance of Strategy 1")
 
#Lets calculate a table of montly returns by year and strategy
table.CalendarReturns(strategies)
 
#Lets make a boxplot of the returns
chart.Boxplot(strategies)
 
#Set the plotting area to a 2 by 2 grid
layout(rbind(c(1,2),c(3,4)))
 
#Plot various histograms with different overlays added
chart.Histogram(strategies[,"Strategy1"], main = "Plain", methods = NULL)
chart.Histogram(strategies[,"Strategy1"], main = "Density", breaks=40, methods = c("add.density", "add.normal"))
chart.Histogram(strategies[,"Strategy1"], main = "Skew and Kurt", methods = c("add.centered", "add.rug"))
chart.Histogram(strategies[,"Strategy1"], main = "Risk Measures", methods = c("add.risk"))
 
#Note: The above histogram plots is taken from the example documentation
#The documentation is excellent
#http://cran.r-project.org/web/packages/PerformanceAnalytics/vignettes/PA-charts.pdf

The performance analytics documentation (including more examples) can be found at:

http://cran.r-project.org/web/packages/PerformanceAnalytics/vignettes/PA-charts.pdf

QuantMod Basics – Stock Data Download and Manipulation

Posted on May 13, 2012 by GekkoQuant

In this quick tutorial I will show you how to use the quantmod library to download historical data, plot it, add a technical indicator (Bollinger Bands) and do some basic manipulation with date ranges and intersecting data sets.

The tutorial will let you make images such as:

This is a very quick tutorial designed to get you started / make you aware of certain packages.

Onto the code:



^?View Code RSPLUS
install.packages("quantmod") #Install the quantmod library
library("quantmod")  #Load the quantmod Library
stockData <- new.env() #Make a new environment for quantmod to store data in
 
startDate = as.Date("2008-01-13") #Specify period of time we are interested in
endDate = as.Date("2012-01-12")
 
tickers <- c("ARM","CSR") #Define the tickers we are interested in
 
#Download the stock history (for all tickers)
getSymbols(tickers, env = stockData, src = "yahoo", from = startDate, to = endDate)
 
#Use head to show first six rows of matrix
head(stockData$ARM)
 
#Lets look at the just the closing prices
Cl(stockData$ARM)
 
#Lets plot the data
chartSeries(stockData$ARM)
 
#Lets add some bollinger bands to the plot (with period 50 & width 2 standard deviations)
?addBBands #Make R display the help documentation so we know what variables to pass to the function
addBBands(n=50, sd=2)
 
#Lets get the technical indicator values saved into a variable
#Note must give it a single time series (I gave it the close price in this example)
indicatorValuesBBands <- BBands(Cl(stockData$ARM),n=50, sd=2)
 
#Lets examine only a 1 month period of data
armSubset<-  window(stockData$ARM, start = as.Date("2010-02-15"), end = as.Date("2010-03-15"))
armSubset #Lets see the data
 
#Lets extract a 1 month period of data for CSR but starting midway through the arm data
csrSubset<-  window(stockData$CSR, start = as.Date("2010-02-25"), end = as.Date("2010-03-25"))
csrSubset #Lets see the data
 
#Now we want to get the intersection of the two subsets of data
#this will gives us all the sets of data where the dates match
#Its important to match the date series to stop spurious analysis of non-synchronised data
#All=FALSE specifies the intersection as in don't include all dates in the merge
armcsrIntersection <- merge(armSubset, csrSubset, all = FALSE)
subset(armcsrIntersection,select = c("ARM.Open","CSR.Open")) #Select the open columns and display

Further material can be found at:

QuantMod Examples http://www.quantmod.com/examples/
QuantMod Documentation http://www.quantmod.com/documentation/quantmod.pdf
Getting Data into R using quantmod http://statmath.wu.ac.at/~hornik/QFS1/quantmod-vignette.pdf
Zoo Quick Reference / How to handle time series data http://cran.r-project.org/web/packages/zoo/vignettes/zoo-quickref.pdf

Gekko Quant – Quantitative Trading

Quantitative Trading, Statistical Arbitrage, Machine Learning and Binary Options

Category Archives: R Code

High Probability Credit Spreads – Using Linear Regression Curves

Parameter Optimisation & Backtesting – Part 2

Trading Strategy – VWAP Mean Reversion

Trading Strategy – S&P VWAP Trend Follow (BUGGY)

Trading Strategy – Volatility Carry Trade

Trading Strategy – Buy on Gap (EPChan)

Stock Data Download & Saving R

Neural Networks with R – A Simple Example

PerformanceAnalytics Basics – Measure Strategy Performance and Risk

QuantMod Basics – Stock Data Download and Manipulation