Image Source: http://www.ritholtz.com/blog/wp-content/uploads/2010/09/Hemline-1-.jpg
Image source: http://alliedow.wordpress.com/2009/11/17/dancing-in-your-nuddy-pants/
•
•
•
•
•
•
•
•
•
•
•
•
•
•

http://xkcd.com/55/
Can signal a change in trends
library(twitteR)
tweets <- searchTwitter("Stock Market", n=1500)
times <- sapply(tweets, function(x) format(x@created, "%b...
http://www.huffingtonpost.com/dan-mirvish/the-hathaway-effect-how-a_b_830041.html
library(RGoogleTrends)
library(quantmod)
ans = getGTrends("Anne Hathaway")
trend <- xts( ans$Week$anne.hathaway, order.by=...
•
•
•

•
•
•
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011
Upcoming SlideShare
Loading in …5
×

Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011

243 views
166 views

Published on

An introduction to emerging alternative data sources available to investors which are increasingly easy to access using R and it's many community-contributed packages.

Presented to the R/Finance conference in Chicago in 2011
http://www.rinfinance.com/RinFinance2011/agenda/

0 Comments
2 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
243
On SlideShare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
6
Comments
0
Likes
2
Embeds 0
No embeds

No notes for slide

Alternative Data Sources for Measuring Market Sentiment and Events (using R) - R/Finance 2011

  1. 1. Image Source: http://www.ritholtz.com/blog/wp-content/uploads/2010/09/Hemline-1-.jpg
  2. 2. Image source: http://alliedow.wordpress.com/2009/11/17/dancing-in-your-nuddy-pants/
  3. 3. • • • •
  4. 4. • • • • • • •
  5. 5. • • • http://xkcd.com/55/
  6. 6. Can signal a change in trends
  7. 7. library(twitteR) tweets <- searchTwitter("Stock Market", n=1500) times <- sapply(tweets, function(x) format(x@created, "%b %d %H:00")) users <- sapply(tweets, function(x) x@screenName) times <- times[!duplicated(users)] # removing duplicate users to avoid spammers and news counts <- table(times) bp <- barplot(counts, main="Counts of 'Stock Market' Tweets by Hour", col="lightblue", border=NA, ylim=c(0,200)) lines(spline(counts ~ bp), lwd=3, lty="dashed", col="darkblue")
  8. 8. http://www.huffingtonpost.com/dan-mirvish/the-hathaway-effect-how-a_b_830041.html
  9. 9. library(RGoogleTrends) library(quantmod) ans = getGTrends("Anne Hathaway") trend <- xts( ans$Week$anne.hathaway, order.by=as.Date(ans$Week$Week, "%b %d %Y")) brk <- getSymbols("BRK-A", auto.assign=F, from = "2004-01-01" ) x <- na.locf(merge(trend, Cl(brk)))[index(trend)] #plot returns and search volume par(mfrow=c(2,1)) plot(x$trend, main="Google Trends: Anne Hathaway", col="blue") plot(x$BRK.A.Close, main="Berkshire Hathaway Share Price", col="red", cex=.7) #evaluate returns by search volume x$Return <- Delt(x$BRK.A.Close) breaks <- cut(x$trend, seq(0,10, 1)) boxplot(as.numeric(x$Return) ~ breaks, ylab="Weekly Return", xlab="Search Volume", col="lightblue", border="darkblue" ) abline(h=0, col="blue")
  10. 10. • • • • • •

×