Online Shopper Intention Analysis Using Conventional Machine Learning And Deep Neural Network Classification Algorithm

Abstract

The use of e-commerce throughout the world in recent years is very rapid. The continuous increase in sales shows that e-commerce has huge market potential. Store profits are derived from the process of assessing data to identify and classify online shopper intentions. The process of assessing the data uses conventional machine learning algorithms and deep neural networks. Comparison of algorithms in this study using the python programming language by knowing the value of Accuracy, F1-Score, Precision, Recall, and ROC AUC. The test results show that the accuracy of the deep neural network algorithm is 98.48%, the F1 score is 95.06%, precision is 97.36%, recall is 96.81% and AUC is 96.81%. So, based on this research, deep neural network data mining techniques can be an effective algorithm for online shopper intention data sets with cross-validation folds of 10, six hidden layer decoder-encoder variations, relu-sigmoid activation function, adagrad optimizer, and learning rate of 0.01 and no dropout. The value of this deep neural network algorithm is quite dominant compared to conventional machine learning algorithms and related research.

Predictive Analysis of User Behavior Processes in Cross-Border E-Commerce Enterprises Based on Deep Learning Models

“…where σ is the sigmoid activation function, a randomly initialized weight matrix W 1 , W 2 is used to map h t , h i into the hidden vector space, and the computed results of the function q are fed into the softmax function for normalization to obtain the weights of each hidden state α. e last step of BiGRU, hidden state h t , is calculated from the last input and the hidden state of the previous state, which can be abstractly understood as the current point of interest or short-term behavioral preferences of the e-commerce user, while the output c t of the attention module is the information extraction for the whole sequence of behaviors, and since the module adaptively focuses on those e-commerce user behaviors that are more important, such as being able to learn that the sequence of e-commerce users clicking on swimming gear is more important, therefore, c t contains the main intention of the e-commerce user during the current behavior, that is, the long-term behavioral preferences of the current sequence. By combining the short-term behavioral preferences h t and long-term behavioral preferences c t of e-commerce users in the current behavior sequence for learning and prediction, not only does it alleviate the problem of losing important information caused by encoding the input sequence as a fixed-length vector by the encoder and making full use of the sequence input information but also allows the model to focus on both the long-term and short-term preferences of e-commerce users in the current sequence, which can improve the prediction effect well [21][22][23].…”

Comparison of Conventional Machine Learning and Deep Neural Network Algorithms in the Prediction of Monkey-Pox

“…An open-source project called Gradient Boosting uses the greedy function approach to create the gradient tree boosting machine learning system, which is effective, quick, and scalable for solving various learning problems. In supervised learning problems, XGBoost predicts the goal variable yi using training data with multiple features xi (Cucu Ika Agustyaningrum, Haris, Aryanti, & Misriati, 2021). f. Support Vector Machine Support Vector Machine (SVM) is an integrated (supervised) classification method that needs specific learning goals during training (Nurachim, 2019).…”

A Streamlined Approach towards Monkeypox Detection

“…A few studies have investigated classical machine learning approaches as alternatives to deep learning. Agustyaningrum et al [7] found that XGBoost outperformed DNNs and CNNs for monkeypox prediction. Maqsood et al [8] used a support vector machine (SVM) on features extracted from Inception-ResNet and NASNet models.…”