Machine Learning (stat.ML)

Abstract: The value of raw data is unlocked by converting it into information and knowledge that drives decision-making. Machine Learning (ML) algorithms are capable of analysing large datasets and making accurate predictions. Market segmentation, client lifetime value, and marketing techniques have all made use of machine learning. This article examines marketing machine learning techniques such as Support Vector Machines, Genetic Algorithms, Deep Learning, and K-Means. ML is used to analyse consumer behaviour, propose items, and make other customer choices about whether or not to purchase a product or service, but it is seldom used to predict when a person will buy a product or a basket of products. In this paper, the survival models Kernel SVM, DeepSurv, Survival Random Forest, and MTLR are examined to predict tine-purchase individual decisions. Gender, Income, Location, PurchaseHistory, OnlineBehavior, Interests, PromotionsDiscounts and CustomerExperience all have an influence on purchasing time, according to the analysis. The study shows that the DeepSurv model predicted purchase completion the best. These insights assist marketers in increasing conversion rates.

Abstract: In this paper, we first reviewed several biclustering methods that are used to identify the most significant clusters in gene expression data. Here we mainly focused on the SSVD(sparse SVD) method and tried a new sparse penalty named "Prenet penalty" which has been used only in factor analysis to gain sparsity. Then in the simulation study, we tried different types of generated datasets (with different sparsity and dimension) and tried 1-layer approximation then for k-layers which shows the mixed Prenet penalty is very effective for non-overlapped data. Finally, we used some real gene expression data to show the behavior of our methods.

Abstract: Some key issues in robust clustering are discussed with focus on Gaussian mixture model based clustering, namely the formal definition of outliers, ambiguity between groups of outliers and clusters, the interaction between robust clustering and the estimation of the number of clusters, the essential dependence of (not only) robust clustering on tuning decisions, and shortcomings of existing measurements of cluster stability when it comes to outliers.

Abstract: Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory demands. In addition, the efficiency of a deep ensemble is related to diversity among the ensemble members which is challenging for large, over-parameterized deep neural networks. Moreover, ensemble learning has not yet seen such widespread adoption, and it remains a challenging endeavor for self-supervised or unsupervised representation learning. Motivated by these challenges, we present a novel self-supervised training regime that leverages an ensemble of independent sub-networks, complemented by a new loss function designed to encourage diversity. Our method efficiently builds a sub-model ensemble with high diversity, leading to well-calibrated estimates of model uncertainty, all achieved with minimal computational overhead compared to traditional deep self-supervised ensembles. To evaluate the effectiveness of our approach, we conducted extensive experiments across various tasks, including in-distribution generalization, out-of-distribution detection, dataset corruption, and semi-supervised settings. The results demonstrate that our method significantly improves prediction reliability. Our approach not only achieves excellent accuracy but also enhances calibration, surpassing baseline performance across a wide range of self-supervised architectures in computer vision, natural language processing, and genomics data.