Selecting Datasets for Evaluating an Enhanced Deep Learning Framework

TL;DR

This paper presents a framework for selecting suitable datasets with irregular sequential patterns to evaluate a deep learning model, concluding that financial market data is most appropriate for testing due to its high irregularity.

Contribution

The work introduces a systematic framework for dataset selection based on outlier detection and peak analysis, tailored for evaluating deep learning models on irregular sequential data.

Findings

Financial market data exhibits high irregularity suitable for evaluation.

The framework effectively identifies datasets with complex sequential patterns.

Selected datasets improve the robustness of deep learning framework testing.

Abstract

A framework was developed to address limitations associated with existing techniques for analysing sequences. This work deals with the steps followed to select suitable datasets characterised by discrete irregular sequential patterns. To identify, select, explore and evaluate which datasets from various sources extracted from more than 400 research articles, an interquartile range method for outlier calculation and a qualitative Billauer's algorithm was adapted to provide periodical peak detection in such datasets. The developed framework was then tested using the most appropriate datasets. The research concluded that the financial market-daily currency exchange domain is the most suitable kind of data set for the evaluation of the designed deep learning framework, as it provides high levels of discrete irregular patterns.