Many critical web applications, from e-commerce price prediction to user engagement forecasting, rely on regression models trained on tabular data. These models often face a dual challenge: the inherent imbalance in continuous target values and, more critically, the unpredictable distribution shifts that occur when the model is deployed online. While data imbalance in classification is well-studied, its intersection with regression tasks in dynamic, real-world settings is underexplored. Existing methods for imbalanced regression often assume that the test data distribution is known and stable, an assumption that rarely holds true for live web systems and can lead to significant performance degradation. To address this gap, we propose a novel framework featuring two key innovations: (i) a Region-Aware Mixture of Experts that leverages a Gaussian Mixture Model to identify distinct data sub-populations. This allows us to synthesize targeted training data and train specialized experts, each tailored to a specific data region. (ii) a Test-Time Self-Supervised Expert Aggregation mechanism. This is the core of our adaptation strategy, dynamically adjusting the weights of each expert based on the features of incoming test instances. This enables our model to adapt on-the-fly to varying test distributions without costly retraining. We evaluated our method on four real-world tabular regression datasets: house pricing, bike sharing, and age prediction. These tasks are representative of real-world scenarios that inherently involve both target imbalance and dynamic distribution shifts (e.g., temporal or market-driven changes). The results demonstrate that our approach significantly outperforms existing imbalanced regression methods, especially under these shifts, achieving an average MAE improvement of 7.1%.

Multivariate time-series forecasting is vital in various domains, e.g., economic planning and weather prediction. Deep train-from-scratch models have exhibited effective performance yet require large amounts of data, which limits real-world applicability. Recently, researchers have leveraged the representation learning transferability of pre-trained Large Language Models (LLMs) to handle limited non-linguistic datasets effectively. However, incorporating LLMs with time-series data presents challenges of limited adaptation due to different compositions between time-series and linguistic data, and the inability to process multi-scale temporal information. To tackle these challenges, we propose LLM4TS, a framework for time-series forecasting with pre-trained LLMs. LLM4TS consists of a two-stage fine-tuning strategy: the time-series alignment stage to align LLMs with the nuances of time-series data and the forecasting fine-tuning stage for downstream time-series forecasting tasks. Furthermore, our framework features a novel two-level aggregation method that integrates multi-scale temporal data within pre-trained LLMs, enhancing their ability to interpret time-specific information. In experiments across seven time-series forecasting datasets, LLM4TS is superior to existing state-of-the-art methods compared with trained-from-scratch models in full-shot scenarios and also achieves the highest rank in few-shot scenarios. In addition, evaluations compared with different unsupervised representation learning approaches highlight LLM4TS’s effectiveness with representation learning in forecasting tasks. Ablation studies further validate each component’s contribution to LLM4TS and underscore the essential role of utilizing LLM’s pre-trained weights for optimal performance. The code is available at https://github.com/blacksnail789521/LLM4TS .

Dynamically planning in complex systems has been explored to improve decision-making in various domains. Professional basketball serves as a compelling example of a dynamic spatio-temporal game, encompassing context-dependent decision-making. However, processing the diverse on-court signals and navigating the vast space of potential actions and outcomes make it difficult for existing approaches to swiftly identify optimal strategies in response to evolving circumstances. In this study, we formulate the sequential decision-making process as a conditional trajectory generation process. Based on the formulation, we introduce PlayBest (PLAYer BEhavior SynThesis), a method to improve player decision-making. We extend the diffusion probabilistic model to learn challenging environmental dynamics from historical National Basketball Association (NBA) player motion tracking data. To incorporate data-driven strategies, an auxiliary value function is trained with corresponding rewards. To accomplish reward-guided trajectory generation, we condition the diffusion model on the value function via classifier-guided sampling. We validate the effectiveness of PlayBest through simulation studies, contrasting the generated trajectories with those employed by professional basketball teams. Our results reveal that the model excels at generating reasonable basketball trajectories that produce efficient plays. Moreover, the synthesized play strategies exhibit an alignment with professional tactics, highlighting the model's capacity to capture the intricate dynamics of basketball games.

Multivariate time-series data in numerous real-world applications (e.g., healthcare and industry) are informative but challenging due to the lack of labels and high dimensionality. Recent studies in self-supervised learning have shown their potential in learning rich representations without relying on labels, yet they fall short in learning disentangled embeddings and addressing issues of inductive bias (e.g., transformation-invariance). To tackle these challenges, we propose TimeDRL, a generic multivariate time-series representation learning frame-work with disentangled dual-level embeddings. TimeDRL is characterized by three novel features: (i) disentangled derivation of timestamp-level and instance-level embeddings from patched time-series data using a [CLS] token strategy; (ii) utilization of timestamp-predictive and instance-contrastive tasks for disentangled representation learning, with the former optimizing timestamp-level embeddings with predictive loss, and the latter optimizing instance-level embeddings with contrastive loss; and (iii) avoidance of augmentation methods to eliminate inductive biases, such as transformation-invariance from cropping and masking. Comprehensive experiments on 6 time-series forecasting datasets and 5 time-series classification datasets have shown that TimeDRL consistently surpasses existing representation learning approaches, achieving an average improvement of forecasting by 58.02% in MSE and classification by 1.48% in accuracy. Further-more, extensive ablation studies confirmed the relative contribution of each component in TimeDRL's architecture, and semi-supervised learning evaluations demonstrated its effectiveness in real-world scenarios, even with limited labeled data. The code is available at https://github.com/blacksnail789521/TimeDRL.

The marketplace system connecting demands and supplies has been explored to develop unbiased decision-making in valuing properties. Real estate appraisal serves as one of the high-cost property valuation tasks for financial institutions since it requires domain experts to appraise the estimation based on the corresponding knowledge and the judgment of the market. Existing automated valuation models reducing the subjectivity of domain experts require a large number of transactions for effective evaluation, which is predominantly limited to not only the labeling efforts of transactions but also the generalizability of new developing and rural areas. To learn representations from unlabeled real estate sets, existing self-supervised learning (SSL) for tabular data neglects various important features, and fails to incorporate domain knowledge. In this paper, we propose DoRA, a Domain-based self-supervised learning framework for low-resource Real estate Appraisal. DoRA is pre-trained with an intra-sample geographic prediction as the pretext task based on the metadata of the real estate for equipping the real estate representations with prior domain knowledge. Furthermore, inter-sample contrastive learning is employed to generalize the representations to be robust for limited transactions of downstream tasks. Our benchmark results on three property types of real-world transactions show that DoRA significantly outperforms the SSL baselines for tabular data, the graph-based methods, and the supervised approaches in the few-shot scenarios by at least 7.6% for MAPE, 11.59% for MAE, and 3.34% for HR10%. We expect DoRA to be useful to other financial practitioners with similar marketplace applications who need general models for properties that are newly built and have limited records. The source code is available at https://github.com/wwweiwei/DoRA.

With the recent progress in sports analytics, deep learning approaches have demonstrated the effectiveness of mining insights into players' tactics for improving performance quality and fan engagement. This is attributed to the availability of public ground-truth datasets. While there are a few available datasets for turn-based sports for action detection, these datasets severely lack structured source data and stroke-level records since these require high-cost labeling efforts from domain experts and are hard to detect using automatic techniques. Consequently, the development of artificial intelligence approaches is significantly hindered when existing models are applied to more challenging structured turn-based sequences. In this paper, we present ShuttleSet, the largest publicly-available badminton singles dataset with annotated stroke-level records. It contains 104 sets, 3,685 rallies, and 36,492 strokes in 44 matches between 2018 and 2021 with 27 top-ranking men's singles and women's singles players. ShuttleSet is manually annotated with a computer-aided labeling tool to increase the labeling efficiency and effectiveness of selecting the shot type with a choice of 18 distinct classes, the corresponding hitting locations, and the locations of both players at each stroke. In the experiments, we provide multiple benchmarks (i.e., stroke influence, stroke forecasting, and movement forecasting) with baselines to illustrate the practicability of using ShuttleSet for turn-based analytics, which is expected to stimulate both academic and sports communities. Over the past two years, a visualization platform has been deployed to illustrate the variability of analysis cases from ShuttleSet for coaches to delve into players' tactical preferences with human-interactive interfaces, which was also used by national badminton teams during multiple international high-ranking matches.

Identifying significant shots in a rally is important for evaluating players’ performance in badminton matches. While there are several studies that have quantified player performance in other sports, analyzing badminton data has remained untouched. In this article, we introduce a badminton language to fully describe the process of the shot, and we propose a deep-learning model composed of a novel short-term extractor and a long-term encoder for capturing a shot-by-shot sequence in a badminton rally by framing the problem as predicting a rally result. Our model incorporates an attention mechanism to enable the transparency between the action sequence and the rally result, which is essential for badminton experts to gain interpretable predictions. Experimental evaluation based on a real-world dataset demonstrates that our proposed model outperforms the strong baselines. We also conducted case studies to show the ability to enhance players’ decision-making confidence and to provide advanced insights for coaching, which benefits the badminton analysis community and bridges the gap between the field of badminton and computer science.

In recent years, a growing body of research has started to explore applying artificial intelligence to the sports industry due to the availability of data and the advancement of techniques. Such applications not only play an important role during matches but also have a great influence on the training stage. However, applying deep learning techniques to sports analytics has several technical challenges, which also remain untouched in badminton analytics as there is no public dataset of stroke event records. Therefore, this dissertation intends to explore challenging research questions and application issues that have not been addressed for benefiting both the research and badminton communities. To achieve the objectives, we, for the first time, propose a unified badminton language to describe the process of the shot, which enables us to conduct downstream applications. Specifically, our first task is to measure the win probability of each shot in badminton matches by considering long-term and short-term dependencies. Second, we introduce a framework with two encoder-decoder extractors and a position-aware fusion network to forecast the possible tactics of players, which is still unexplored in turn-based sports. To provide the transparency of these models, we aim to design a post-hoc explainer by computing feature attributions with Shapley values as the third task. In this manner, researchers can investigate model behaviors for advanced improvement, and the badminton community benefits from coaching the players and determining the strategies. This dissertation is supervised by Wen-Chih Peng ([email protected]).

Identifying significant shots in a rally is important for evaluating players’ performance in badminton matches. While there are several studies that have quantified player performance in other sports, analyzing badminton data is remained untouched. In this paper, we introduce a badminton language to fully describe the process of the shot and propose a deep learning model composed of a novel short-term extractor and a long-term encoder for capturing a shot-by-shot sequence in a badminton rally by framing the problem as predicting a rally result. Our model incorporates an attention mechanism to enable the transparency of the action sequence to the rally result, which is essential for badminton experts to gain interpretable predictions. Experimental evaluation based on a real-world dataset demonstrates that our proposed model outperforms the strong baselines. The source code is publicly available at https://github.com/wywyWang/Shot-Influence.