neighbours of the current indicator(s) values. collected in 3 arrays - feature1, feature2 and directions, - and finds the k-nearest To do a prediction of the next market move, the kNN algorithm uses the historic data, Being an unsupervised machine learning algorithm, kNN is one of the most simple learning algorithms. to let you find a prediction for the next (tomorrow's, next month's, etc.) market move. This strategy uses a classic machine learning algorithm - k Nearest Neighbours (kNN). in order for the users to see the differences. I intentionally decided to publish this script separately Now this script works in all timeframes ! an adjustible k value for the kNN model, This update to the popular kNN-based strategy features: © Learning: kNN-based Strategy (update)", '', true, precision=4, max_labels_count=200) This source code is subject to the terms of the Mozilla Public License 2.0 at The script can be found here: Ĭould someone please convert it, I'd greatly appreciate it. The indicator supposedly is quite good in backtesting and would love to use with ThinkorSwim.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |