Favorite data mining quote

Below is my favorite data mining related quote:

The capacity of digital data storage worldwide has doubled every nine months for at least a decade, at twice the rate predicted by Moore’s Law for the growth of computing power during the same period.” (Fayyad et al., 2002)

It can be mentioned to justify the overall success of data mining. Personally, I use it as an introductory slide in most of my presentations related to data mining. Feel free to add the data mining quotes you like as a comment to this post.

Fayyad, U. and Uthurusamy R., Evolving data mining into solutions for insights, Communications of the ACM, Vol. 45, No. 8, 2002, pp. 28-31.


Recommended Reading

Comments Icon5 comments found on “Favorite data mining quote

  1. From a user’s prospective: most data become of little value or useless after like 5 years… even the same data had been vital to the user..

  2. Your comment is definitely right. However, I think that in some applications, old data remain interesting (for example weather forecasting).

  3. I agree. some data remain interesting and their analysis is often important. For example: from a stock’s perspective, it is always good to know how the company’s stock has been performing from the past 10 years. Further understanding the market, helps analysts make better predictions of how the market may react to a certain news.

  4. the past surely does not describe the future, especially when it comes to the stock market. If it would, I would be rich by now – I am not – thus no past use for future predictions: Q.e.d. 😉

    What I consider to be thought about is that with every piece of knowledge we obtain, we get a view from the world and people base their decisions on this knowledge. By getting some knowledge, this part of knowledge (if accepted as right) therefore steers the world as long as its proven “wrong”. So we actually create our reality ourselves, e.g. we eat meat – is it good or bad? we really don’t know for sure – we might not even be able to get a objective response to the question – but we all (most) do. maybe what i try to say: we are to damn stupid 😉

  5. @call me crazy: “the past surely does not describe the future”… if that was true, data mining and machine learning fields would not exist 🙂

    What we can say is that past performances (using predictive analytics) are not a guarantee of future performances. This is particularly true in finance. The fact that it is difficult to predict the stock market, even with machine learning, is due to the lack of information in the model.

    By using only technical and fundamental indicators, we miss most of the data that could be used to predict the stock market. Some data exist but are too vast to be used in the model (e.g. economic facts, politics, gossip, etc.). Some are even not measured such as emotions, which is maybe the most important predictor for stock market.

Comments are closed.