High Utility Item Set Mining in Transactional Data using a Deep Learning Model

High Utility Itemset Mining (HUIM) is an essential method in the data mining sector that helps find itemsets in transactional data that are suitable. This research proposes a original technique for HUIM by integrating Deep Learning (DL) approaches to evolution both accuracy and efficiency. We provide a DL technique that uses a neural network architecture to quantify and dynamically extract high utility itemsets (HUIs) from huge transactional datasets. In particular, the method combines Long Short-Term Memory (LSTM) networks to record sequential dependencies within transactions with Convolutional Neural Networks (CNNs) for feature extraction. To additional development performance, we integrate an Ant Colony Optimization (ACO) algorithm for optimizing the DL approaches hyperparameters and the feature selection procedure. Experimental evaluation on benchmark transactional datasets, demonstrating significant improvements in mining accuracy, processing time, and overall utility discovery related to traditional HUIM approaches, providing a robust framework for data analysis and decision-making in many domains.