Gilder and Lerman hypothesised that past/present events can potentially assist in predicting future prices in prediction markets. They empirically revealed that prediction markets are surprisingly predictable, even by purely market-historical techniques.

Taking hold of the baton from Gilder and Lerma, Panos Ipeirotis and George Tziralis developed techniques for extracting news flow signals to see whether they can indeed be utilised to predict the future performance of markets on the InTrade prediction exchange. On the question of whether Hillary Clinton will be the Democratic Presidential Nominee in 2008, they noted-

Our sentiment index (in maroon) is close to 1 when we predict that the market will move higher, and it is close to 0 when we predict that the market will move down. Typically, it works pretty well for predicting long periods of price increases and declines. To put our money where our mouth is, the signal for the last few days shows that Hillary&#8217-s market price will edge lower in the next few days/weeks.

Following on from this we looked at the Intrade prediction market and the Betfair markets on whether Hillary Clinton will be the Democratic Presidential Nominee in 2008, as of 10.45 GMT on December 3 2007. Whilst the Intrade market suggested that Clinton&#8217-s probability of victory was 67%, the Betfair market gave a reading of 69%.

We returned to the Intrade prediction market and the Betfair market on whether Hillary Clinton will be the Democratic Presidential Nominee in 2008 at 08.45 GMT on December 7 2007.

Whilst the Intrade prediction market had previously suggested that Clinton&#8217-s probability of victory was 67%, it was now suggesting that her probability of victory was 64%.

The Betfair market which had given a reading of 69% on Decmber 3 as regards her probability of winning the democratic nomination, was now suggesting that her probability of victory was only 50%.

It is quite clear, that the both sets of markets are responding to stale news, with Intrade significantly lagging behind Betfair, as regards its ability to aggregate all available news flow. Those that had sold Clinton on Betfair at 1.44 on December 3, on the back of Panos Ipeirotis and George Tziralis&#8217- advice, are now sitting on a healthy profit. The claim that prediction markets are innefficient would seem to be gathering momentum&#8230-. with the most likely cause being the fact that they are not liquid enough.

http://www.bettingmarket.com/predictionstale.htm