Financial organizations collect a huge amount of data about clients that typically has a temporal (sequential) structure and is collected from various sources (modalities). Due to privacy issues, there are no large-scale open-source multimodal datasets of event sequences, which significantly limits the research in this area. In this paper, we present the industrial-scale publicly available multimodal banking dataset, MBD, that contains more than 1.5M corporate clients with several modalities: 950M bank transactions, 1B geo position events, 5M embeddings of dialogues with technical support and monthly aggregated purchases of four bank's products. All entries are properly anonymized from real proprietary bank data. Using this dataset, we introduce a novel benchmark with two business tasks: campaigning (purchase prediction in the next month) and matching of clients. We provide numerical results that demonstrate the superiority of our multi-modal baselines over single-modal techniques for each task. As a result, the proposed dataset can open new perspectives and facilitate the future development of practically important large-scale multimodal algorithms for event sequences. HuggingFace Link: https://huggingface.co/datasets/ai-lab/MBD Github Link: https://github.com/Dzhambo/MBD

Forecasting future events over extended periods, known as long-horizon prediction, is a fundamental task in various domains, including retail, finance, healthcare, and social networks. Traditional methods, such as Marked Temporal Point Processes (MTPP), typically use autoregressive models to predict multiple future events. However, these models frequently encounter issues such as converging to constant or repetitive outputs, which significantly limits their effectiveness and applicability. To overcome these limitations, we propose DeTPP (Detection-based Temporal Point Processes), a novel approach inspired by object detection methods from computer vision. DeTPP utilizes a novel matching-based loss function that selectively focuses on reliably predictable events, enhancing both training robustness and inference diversity. Our method sets a new state-of-the-art in long-horizon event prediction, significantly outperforming existing MTPP and next-K approaches. The implementation of DeTPP is publicly available on GitHub.

Event sequences (ESs) arise in many practical domains including finance, retail, social networks, and healthcare. In the context of machine learning, event sequences can be seen as a special type of tabular data with annotated timestamps. Despite the importance of ESs modeling and analysis, little effort was made in adapting large language models (LLMs) to the ESs domain. In this paper, we highlight the common difficulties of ESs processing and propose a novel solution capable of solving multiple downstream tasks with little or no finetuning. In particular, we solve the problem of working with long sequences and improve time and numeric features processing. The resulting method, called ESQA, effectively utilizes the power of LLMs and, according to extensive experiments, achieves state-of-the-art results in the ESs domain.

In sequential event prediction, which finds applications in finance, retail, social networks, and healthcare, a crucial task is forecasting multiple future events within a specified time horizon. Traditionally, this has been addressed through autoregressive generation using next-event prediction models, such as Marked Temporal Point Processes. However, autoregressive methods use their own output for future predictions, potentially reducing quality as the prediction horizon extends. In this paper, we challenge traditional approaches by introducing a novel benchmark, HoTPP, specifically designed to evaluate a model's ability to predict event sequences over a horizon. This benchmark features a new metric inspired by object detection in computer vision, addressing the limitations of existing metrics in assessing models with imprecise time-step predictions. Our evaluations on established datasets employing various models demonstrate that high accuracy in next-event prediction does not necessarily translate to superior horizon prediction, and vice versa. HoTPP aims to serve as a valuable tool for developing more robust event sequence prediction methods, ultimately paving the way for further advancements in the field.

Classification tasks are usually evaluated in terms of accuracy. However, accuracy is discontinuous and cannot be directly optimized using gradient ascent. Popular methods minimize cross-entropy, hinge loss, or other surrogate losses, which can lead to suboptimal results. In this paper, we propose a new optimization framework by introducing stochasticity to a model's output and optimizing expected accuracy, i.e. accuracy of the stochastic model. Extensive experiments on linear models and deep image classification show that the proposed optimization method is a powerful alternative to widely used classification losses.

Deep ensembles are capable of achieving state-of-the-art results in classification and out-of-distribution (OOD) detection. However, their effectiveness is limited due to the homogeneity of learned patterns within ensembles. To overcome this issue, our study introduces Saliency Diversified Deep Ensemble (SDDE), a novel approach that promotes diversity among ensemble members by leveraging saliency maps. Through incorporating saliency map diversification, our method outperforms conventional ensemble techniques and improves calibration in multiple classification and OOD detection tasks. In particular, the proposed method achieves state-of-the-art OOD detection quality, calibration, and accuracy on multiple benchmarks, including CIFAR10/100 and large-scale ImageNet datasets.

The concepts of overfitting and generalization are vital for evaluating machine learning models. In this work, we show that the popular Recall@K metric depends on the number of classes in the dataset, which limits its ability to estimate generalization. To fix this issue, we propose a new metric, which measures retrieval performance, and, unlike Recall@K, estimates generalization. We apply the proposed metric to popular image retrieval methods and provide new insights about deep metric learning generalization.