My blog has moved! Redirecting...

You should be automatically redirected. If not, visit and update your bookmarks.

Data Mining Research - Influencing predictions

I'm a Data Miner Collection (T-shirts, Mugs & Mousepads)

All benefits are given to a charity association.

Sunday, May 25, 2008

Influencing predictions

As you may know, I have started applying data mining in a small financial company in Switzerland. I have thus read some books about technical analysis. The aim of technical analysis is to use technical indicators (that are based on daily stock prices) to predict the future trends of stocks in the short or mid term. I was surprised to read in a book that the author compares stock market predictions with weather forecasting.

I personally think that there is a big difference between these two tasks (at least conceptually). It concerns the influence of your predictions. With the stock market, people are using technical analysis to buy and sell and thus influencing what they are predicting. Millions of traders and quantitative analysts in the world are using the same set of tools and acting consequently. This is not the case with weather forecasting. Even if millions of people can predict exactly the weather for the next day, it won't change anything to the weather of tomorrow. This is an interesting difference between these two tasks.

Of course, stock market is not only dependent on traders who believe in technical analysis. Most of the influence certainly comes from the offer/demand couple as well as every day news. Also, several people around the world do not base their strategies on technical analysis but rather on fundamentals (information coming directly from companies). What do you think of this issue? Are technical analysts really influencing their own predictions? Feel free to post your opinion.

Sphere: Related Content


Will Dwinnell said...

It is probably worth considering the difference between technical analysts as individual forecasters and as a group.

As you've noted, the market is composed of more than technical analysts, but everyone who enters the market is making some sort of prediction, even is only as crude and vague as "my investment will go up". At this level, the market is really only composed of entities (people, organizations and machines) making predictions.

At another level though- that of the individual technical analyst, I suspect that the predictions of the individual in most cases will likely have very little affect on the subsequent behavior of the market.

To be clear: I am suggesting that, at the level of the individual technical analyst and his investments over any given year, the year-end difference between the two hypothetical markets (one in which the investor participated, the other in which he did not) is likely negligible.

Sandro Saitta said...

Will, I definitely agree on the first part of your comment. Regarding the second part, I think that technical analysts may be considered as one group. Mainly because they basically use the same tools and should therefore react in the same way to indices and individual stocks variations. However, I agree that if you consider them individually, their are not influencing the market.

Anonymous said...

It's the aggregate behaviour that is reflected in the overall price as each trade relects a bid hitting an ask for quantity X from one or more entities or their agents.


Jeffrey Austin White said...

I have developed my own theory on the markets. I would be interested to find out if you can apply your technique to my Audibles theory. Please check it out and give me your feedback.

Audible Theory

Sandro Saitta said...

Thanks for sharing your work Jeffrey. I will follow what you do with your next posts. It would be interesting to have some backtest results (for example for 2000-2007).

Anonymous said...

Very interesting blog. I'm interested in data mining the stock market myself. Just learning about data mining but was a stock daytrader for years and now looking to trade longer time frames based on technicals.

I would love to get data going back to the early 1900's if I can find it. Any recommendations on where to get the daily data from?

I suppose everyone has their favorite books on trading. One of mine is "How To Make Money in Stocks" by William J. O'Neil. He is the founder of the Investor's Business Daily. - Scott from Florida

Georg Ruß said...

Does financial stock forecasting really work? I'm really skeptical for a theoretical reason: if everyone used the same model and acted the same upon its prediction, then this would probably crash the prediction. Market prices are essentially obtained from buying/selling decisions of traders, so if everyone wants to buy, the price goes up.

Of course, not everyone uses the same model, but imagine they would. I certainly can imagine that forecasting works up to a certain degree, but not for everyone.

Sandro Saitta said...

Scott: Thanks for you comment. I think it is not easy to find daily financial data before the 80's. To my knowledge, Bloomberg is providing data only from the late 80's.

Georg: You comment is very interesting. I do believe that this problem may happen, especially for technical analysis since plenty of analysts make use of it. However, if we think globally, predictions using data mining, technical analysis or other techniques are certainly very different. So I think that they are not influing the market the same way (but this is only a supposition).

Clicky Web Analytics