Discussing the article: "MQL5 Wizard Techniques you should know (Part 13). DBSCAN for Expert Signal Class"
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
Check out the new article: MQL5 Wizard Techniques you should know (Part 13). DBSCAN for Expert Signal Class.
Density Based Spatial Clustering for Applications with Noise is an unsupervised form of grouping data that hardly requires any input parameters, save for just 2, which when compared to other approaches like k-means, is a boon. We delve into how this could be constructive for testing and eventually trading with Wizard assembled Expert Advisers
These series of articles, on the MQL5 Wizard, are a segue on how often abstract ideas in Mathematics of other fields of life can be enlivened as trading systems and tested or validated before any serious commitments is made on their premise. This ability to take simple and not fully implemented or envisaged ideas and explore their potential as trading systems is one of the gems presented by the MQL5 wizard assembly for expert advisers. The expert classes of the wizard furnish a lot of the mundane features required by any expert adviser especially as it relates to opening and closing trades but also in overlooked aspects like executing decisions only on a new bar formation.
So, in keeping this library of processes as a separate aspect of an expert adviser, with the MQL5 Wizard any idea can not only be tested independently, but also compared on a somewhat equal footing to any other ideas (or methods) that could be under consideration. In these series we have looked at alternative clustering methods like the agglomerative clustering as well as the k-means clustering.
In each of these approaches, prior to generating the respective clusters, one of the required input parameters was the number of clusters to be created. This in essence assumes that the user is well versed with the data set and is not exploring or looking at unfamiliar dataset. With Density Based Spatial Clustering for Applications with Noise (DBSCAN) the number of clusters to be formed is a ‘respected’ unknown. This affords more flexibility not just in exploring unknown data sets and discovering their major classification traits, but it can also allow checking existing ‘biases’ or commonly held views on any given data set for whether the number of clusters assumed can be verified.
By taking just two parameters namely epsilon, which is the maximum spatial distance between points in a cluster; and the number of minimum points required to constitute a cluster, DBSCAN is able to not only generate clusters from sampled data, but also determine the appropriate number of these clusters. To appreciate its remarkable feats, it may be helpful to look at some clustering it can perform as opposed to alternative approaches.
According to this public article on medium, DBSCAN and k-means clustering would, by their definition give these separate clustering results.
For k-means clustering we would have:
while DBSCAN would give:
Author: Stephen Njuki