Friday, September 23, 2011

Twitter Sentiment based trading algo



Came across this from slashdot, apparently Derwent Capital has created an algo to forecast market moves off twitter sentiment with relatively high accuracy.

"
The number of emotional words on Twitter could be used to predict daily moves in the Dow Jones Industrial Average. A change in emotions expressed online would be followed between two and six days later by a move in the index, the researchers said, and this information let them predict its movements with 87.6 percent accuracy (historically)

"
This is in line with the idea of text based sentiment estimation. There's a number of quant finance research effort around this area, though I haven't seen much of it from practicing firms. Perhaps they just aren't talking about it. Remember the Hot Chicks Indicator? yeah, it's kinda like that.

0 Reflections: