You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
New article Neural networks made easy (Part 18): Association rules has been published:
As a continuation of this series of articles, let's consider another type of problems within unsupervised learning methods: mining association rules. This problem type was first used in retail, namely supermarkets, to analyze market baskets. In this article, we will talk about the applicability of such algorithms in trading.
The algorithm starts by eliminating random items. To do this, like in the previous algorithm, we perform the first pass for the entire training set and calculate the support for each item. After that delete all items with the frequency less than MinSup.
The remaining items are arranged in descending order of their supports. The above example results in the following series:
D (0.8) -> C (0.7) -> B (0.6) -> E(0.4)
Next, we will grow the FP-tree. To do this, implement the second pass over the training sample. In each transaction, we only take frequent items arranged in descending order of supports and build a path in the tree. Thus, the node with the highest support will be in the tree root, while that with the lowest one will be a leaf. We also create a counter for each node. At the first iteration, we set the counter value equal to 1 (or 1/N, where N is the size of the training sample).
Author: Dmitriy Gizlyk