Short-term prediction through ordinal patterns
Neuman, Yair; Neuman, Yair; Cohen, Yohai; Tamir, Boaz (2021), Short-term prediction through ordinal patterns, Dryad, Dataset, https://doi.org/10.5061/dryad.vq83bk3r9
Prediction in natural environments is a challenging task, and there is a lack of clarity around how a myopic organism can make short-term predictions given limited data availability and cognitive resources. In this context, we may ask what kind of resources are available to the organism to help it address the challenge of short-term prediction within its own cognitive limits. We point to one potentially important resource: ordinal patterns, which are extensively used in physics but not in the study of cognitive processes. We explain the potential importance of ordinal patterns for short-term prediction, and how natural constraints imposed through (1) ordinal pattern types, (2) their transition probabilities and (3) their irreversibility signature may support short-term prediction. Having tested these ideas on a massive data set of Bitcoin prices representing a highly fluctuating environment, we provide preliminary empirical support showing how organisms characterized by bounded rationality may generate short-term predictions by relying on ordinal patterns.
The data file holds 60000 samples of 62 minutes of trade prices in permutations form of the bitcoin exchange bitstamp
The readme files contain the explanation of the code for the article.
The main function has the code for the run and only the local path for the files directory is needed to be changed.
The epoch variable is the window size to use and can be up to 60.