IntLevPy: A Python library to classify and model intermittent and Lévy processes
Year: 2025
Type: software-paper
Abstract: IntLevPy provides a comprehensive description of the IntLevPy Package, a Python library designed for simulating and analyzing intermittent and Lévy processes. The package includes functionalities such as full parameter estimation and fitting optimization for both families of processes, as well as moment calculation, and classification methods. More specifically, as an optimized model for specific datasets, it retrieves the respective parameter values. As for the classification methodology, it utilizes adjusted-R2 and an effective performance measure Γ, enabling the distinction between intermittent and Lévy processes. As a ready-to-use set of routines, it enables to compute statistical moments of stochastic data series and derive model fitting, integrating iterative parameter optimization with simulation-based validation. Moreover, we also address concrete use-cases, showing IntLevPy’s application through synthetic and real-world eye-tracking data. The open-source package includes comprehensive unit tests for reliability, making it easily extensible. All in all, IntLevPy facilitates systematic exploration of these two broad classes of stochastic processes, bridging theoretical models and practical applications.
Source: SoftwareX
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,200
Funder: Norges Forskningsråd
Award: G7609097805
OpenAlex ID: W4413963449