An Analysis of Sequential Pattern Mining Approach for Progressive Database by Deep Learning Technique

In the disciplines of enterprise, electronic commerce, bioinformatics, and other related subjects, sequential form mining is one of the most broadly utilized approaches. Traditional techniques are unable to accurately mine massive amounts of data due to their inherent limitations. Thus, the suggested study makes use of Deep Structured Learning-based Sequent form mining to reduce the complexity associated with dealing with large amounts of data. Data in application sectors like banking and e-commerce are prone to dynamic changes, increasing non-stationarity. To convert the data to a stochastic/time series format, employing wavelet analysis has been suggested. A modified Long Short-Term Memory (LSTM) was also built to increase mining precision. By removing old data from a progressive database, the recommended technique extracts the sequential pattern. To demonstrate the robustness of the suggested work, the execution time of the proposed work is compared to that of traditional algorithms.