Qiwei Han

Alessandro Gambetti, Qiwei Han, Cláudia Soares et al.

Vision-Language Models (VLMs) struggle when applied to medical image-text data, yet the tools available to diagnose this failure remain limited. Existing representation alignment metrics are symmetric, collapsing both modalities into a single score and hiding which modality drives cross-modal degradation. We introduce the Spectral Alignment Score (SAS), an asymmetric metric that projects both modalities onto the principal eigenbasis of an anchor modality and computes eigenvalue-weighted per-eigenmode correlations, resulting in directional scores whose difference quantifies modality information imbalance. We embed SAS within a benchmarking framework evaluating 15 VLMs across natural and medical image-text datasets alongside 6 alignment metrics and bidirectional retrieval. Our experiments show that medical images retain richer structural information than their paired clinical reports, a directional asymmetry invisible to all competing metrics, and that SAS achieves the strongest zero-label correlation with retrieval performance in the medical domain, positioning it as a practical diagnostic tool for clinical deployment. Code is available at this URL: https://github.com/iamalegambetti/medical-vlms-assessment.

Filipa Valdeira, Stevo Racković, Valeria Danalachi et al.

Recommendation Systems (RS) are often used to address the issue of medical doctor referrals. However, these systems require access to patient feedback and medical records, which may not always be available in real-world scenarios. Our research focuses on medical referrals and aims to predict recommendations in different specialties of physicians for both new patients and those with a consultation history. We use Extreme Multilabel Classification (XML), commonly employed in text-based classification tasks, to encode available features and explore different scenarios. While its potential for recommendation tasks has often been suggested, this has not been thoroughly explored in the literature. Motivated by the doctor referral case, we show how to recast a traditional recommender setting into a multilabel classification problem that current XML methods can solve. Further, we propose a unified model leveraging patient history across different specialties. Compared to state-of-the-art RS using the same features, our approach consistently improves standard recommendation metrics up to approximately $10\%$ for patients with a previous consultation history. For new patients, XML proves better at exploiting available features, outperforming the benchmark in favorable scenarios, with particular emphasis on recall metrics. Thus, our approach brings us one step closer to creating more effective and personalized doctor referral systems. Additionally, it highlights XML as a promising alternative to current hybrid or content-based RS, while identifying key aspects to take into account when using XML for recommendation tasks.

Alessandro Gambetti, Qiwei Han

Recent advances in generative models such as GPT may be used to fabricate indistinguishable fake customer reviews at a much lower cost, thus posing challenges for social media platforms to detect these machine-generated fake reviews. We propose to leverage the high-quality elite restaurant reviews verified by Yelp to generate fake reviews from the OpenAI GPT review creator and ultimately fine-tune a GPT output detector to predict fake reviews that significantly outperform existing solutions. We further apply the model to predict non-elite reviews and identify the patterns across several dimensions, such as review, user and restaurant characteristics, and writing style. We show that social media platforms are continuously challenged by machine-generated fake reviews, although they may implement detection systems to filter out suspicious reviews.

Fynn Oldenburg, Qiwei Han, Maximilian Kaiser

As advertisers increasingly shift their budgets toward digital advertising, accurately forecasting advertising costs becomes essential for optimizing marketing campaign returns. This paper presents a comprehensive study that employs various time-series forecasting methods to predict daily average CPC in the online advertising market. We evaluate the performance of statistical models, machine learning techniques, and deep learning approaches, including the Temporal Fusion Transformer (TFT). Our findings reveal that incorporating multivariate models, enriched with covariates derived from competitors' CPC patterns through time-series clustering, significantly improves forecasting accuracy. We interpret the results by analyzing feature importance and temporal attention, demonstrating how the models leverage both the advertiser's data and insights from the competitive landscape. Additionally, our method proves robust during major market shifts, such as the COVID-19 pandemic, consistently outperforming models that rely solely on individual advertisers' data. This study introduces a scalable technique for selecting relevant covariates from a broad pool of advertisers, offering more accurate long-term forecasts and strategic insights into budget allocation and competitive dynamics in digital advertising.

Sebastian Frey, Edoardo Beccari, Maximilian Kranz et al.

Cost-per-click (CPC) in paid search is a volatile auction outcome generated by a competitive landscape that is only partially observable from any single advertiser's history. Using Google Ads auction logs from a concentrated car-rental market (2021--2023), we forecast weekly CPC for 1,811 keyword series and approximate latent competition through complementary signals derived from keyword text, CPC trajectories, and geographic market structure. We construct (i) semantic neighborhoods and a semantic keyword graph from pretrained transformer-based representations of keyword text, (ii) behavioral neighborhoods via Dynamic Time Warping (DTW) alignment of CPC trajectories, and (iii) geographic-intent covariates capturing localized demand and marketplace heterogeneity. We extensively evaluate these signals both as stand-alone covariates and as relational priors in spatiotemporal graph forecasters, benchmarking them against strong statistical, neural, and time-series foundation-model baselines. Across methods, competition-aware augmentation improves stability and error profiles at business-relevant medium and longer horizons, where competitive regimes shift and volatility is most consequential. The results show that broad market-outcome coverage, combined with keyword-derived semantic and geographic priors, provides a scalable way to approximate latent competition and improve CPC forecasting in auction-driven markets.

Carolina Aparício, Qi Shi, Bo Wen et al.

Addressing the challenge of multimodal data fusion in high-dimensional biomedical informatics, we propose MMCTOP, a MultiModal Clinical-Trial Outcome Prediction framework that integrates heterogeneous biomedical signals spanning (i) molecular structure representations, (ii) protocol metadata and long-form eligibility narratives, and (iii) disease ontologies. MMCTOP couples schema-guided textualization and input-fidelity validation with modality-aware representation learning, in which domain-specific encoders generate aligned embeddings that are fused by a transformer backbone augmented with a drug-disease-conditioned sparse Mixture-of-Experts (SMoE). This design explicitly supports specialization across therapeutic and design subspaces while maintaining scalable computation through top-k routing. MMCTOP achieves consistent improvements in precision, F1, and AUC over unimodal and multimodal baselines on benchmark datasets, and ablations show that schema-guided textualization and selective expert routing contribute materially to performance and stability. We additionally apply temperature scaling to obtain calibrated probabilities, ensuring reliable risk estimation for downstream decision support. Overall, MMCTOP advances multimodal trial modeling by combining controlled narrative normalization, context-conditioned expert fusion, and operational safeguards aimed at auditability and reproducibility in biomedical informatics.

Marco Piccolo, Qiwei Han, Astrid van Toor et al.

Marine biodiversity monitoring requires scalability and reliability across complex underwater environments to support conservation and invasive-species management. Yet existing detection solutions often exhibit a pronounced deployment gap, with performance degrading sharply when transferred to new sites. This work establishes the foundational detection layer for a multi-year invasive species monitoring initiative targeting Arctic and Atlantic marine ecosystems. We address this challenge by developing a Unified Information Pipeline that standardises heterogeneous datasets into a comparable information flow and evaluates a fixed, deployment-relevant detector under controlled cross-domain protocols. Across multiple domains, we find that structural factors, such as scene composition, object density, and contextual redundancy, explain cross-domain performance loss more strongly than visual degradation such as turbidity, with sparse scenes inducing a characteristic "Context Collapse" failure mode. We further validate operational feasibility by benchmarking inference on low-cost edge hardware, showing that runtime optimisation enables practical sampling rates for remote monitoring. The results shift emphasis from image enhancement toward structure-aware reliability, providing a democratised tool for consistent marine ecosystem assessment.

Alessandro Gambetti, Qiwei Han, Hong Shen et al.

Explainable Artificial Intelligence (XAI) is essential for the transparency and clinical adoption of Clinical Decision Support Systems (CDSS). However, the real-world effectiveness of existing XAI methods remains limited and is inconsistently evaluated. This study conducts a systematic PRISMA-guided survey of 31 human-centered evaluations (HCE) of XAI applied to CDSS, classifying them by XAI methodology, evaluation design, and adoption barrier. Our findings reveal that most existing studies employ post-hoc, model-agnostic approaches such as SHAP and Grad-CAM, typically assessed through small-scale clinician studies. The results show that over 80% of the studies adopt post-hoc, model-agnostic approaches such as SHAP and Grad-CAM, and that clinician sample sizes remain below 25 participants. The findings indicate that explanations generally improve clinician trust and diagnostic confidence, but frequently increase cognitive load and exhibit misalignment with domain reasoning processes. To bridge these gaps, we propose a stakeholder-centric evaluation framework that integrates socio-technical principles and human-computer interaction to guide the future development of clinically viable and trustworthy XAI-based CDSS.

Luca Silvano Carocci, Qiwei Han

This study presents a novel application of Graph Neural Networks (GNNs) to optimize dealership network planning for a luxury car manufacturer in the U.S. By conducting a comprehensive literature review on dealership location determinants, the study identifies 65 county-level explanatory variables, augmented by two additional measures of regional interconnectedness derived from social and mobility data. An ablation study involving 34 variable combinations and ten state-of-the-art GNN operators reveals key insights into the predictive power of various variables, particularly highlighting the significance of competition, demographic factors, and mobility patterns in influencing dealership location decisions. The analysis pinpoints seven specific counties as promising targets for network expansion. This research not only illustrates the effectiveness of GNNs in solving complex geospatial decision-making problems but also provides actionable recommendations and valuable methodological insights for industry practitioners.

Yimeng Qiu, Qiwei Han

This paper investigates how similarity in the informational representation of market states among Artificial Intelligence (AI) trading agents can generate systemic instability in financial markets. We construct a structural multi-agent market model calibrated using high-frequency microstructural moments. AI agents are modeled through a two-layer decision architecture consisting of a nonlinear representation layer and an adaptive linear readout layer. The representation layer maps raw market states into high-dimensional feature vectors, while the readout layer generates return forecasts that feed into a risk-controlled trading rule. This representation-based microfoundation separates two objects that are often conflated in the literature: representation homogeneity (the degree to which agents encode market states into similar feature spaces) and forecast overlap (the degree to which agents produce similar return predictions). We show theoretically that these two concepts are related but not equivalent, and that representation homogeneity can compress the effective space of forecast disagreement under stress even when predictions appear diverse in normal times. Through controlled factorial experiments that vary representation homogeneity while conditioning on alternative risk-aversion and learning-rate distributions, we hypothesize that increasing representation similarity amplifies synchronization in beliefs and positions, leading to volatility clustering, liquidity stress, and elevated tail risk. Our structural mechanisms suggest that low perceived volatility regimes can endogenously accumulate hidden leverage through position stickiness, which subsequently collapses when shocks trigger synchronized deleveraging. The results provide a structural foundation for macroprudential policies aimed at monitoring and preserving diversity in how AI systems represent and process market information.

Regina de Brito Duarte, Qiwei Han, Claudia Soares

Medical referrals between primary care physicians (PC) and specialist care (SC) physicians profoundly impact patient care regarding quality, satisfaction, and cost. This paper investigates the influence of professional networks among medical doctors on referring patients from PC to SC. Using five-year consultation data from a Portuguese private health provider, we conducted exploratory data analysis and constructed both professional and referral networks among physicians. We then apply Graph Neural Network (GNN) models to learn latent representations of the referral network. Our analysis supports the hypothesis that doctors' professional social connections can predict medical referrals, potentially enhancing collaboration within organizations and improving healthcare services. This research contributes to dissecting the underlying mechanisms in primary-specialty referrals, thereby providing valuable insights for enhancing patient care and effective healthcare management.

Lotte Gross, Rebecca Walter, Nicole Zoppi et al.

This study addresses critical industrial challenges in e-commerce product categorization, namely platform heterogeneity and the structural limitations of existing taxonomies, by developing and deploying a multimodal hierarchical classification framework. Using a dataset of 271,700 products from 40 international fashion e-commerce platforms, we integrate textual features (RoBERTa), visual features (ViT), and joint vision-language representations (CLIP). We investigate fusion strategies, including early, late, and attention-based fusion within a hierarchical architecture enhanced by dynamic masking to ensure taxonomic consistency. Results show that CLIP embeddings combined via an MLP-based late-fusion strategy achieve the highest hierarchical F1 (98.59%), outperforming unimodal baselines. To address shallow or inconsistent categories, we further introduce a self-supervised "product recategorization" pipeline using SimCLR, UMAP, and cascade clustering, which discovered new, fine-grained categories (for example, subtypes of "Shoes") with cluster purities above 86%. Cross-platform experiments reveal a deployment-relevant trade-off: complex late-fusion methods maximize accuracy with diverse training data, while simpler early-fusion methods generalize more effectively to unseen platforms. Finally, we demonstrate the framework's industrial scalability through deployment in EURWEB's commercial transaction intelligence platform via a two-stage inference pipeline, combining a lightweight RoBERTa stage with a GPU-accelerated multimodal stage to balance cost and accuracy.

Bo Wen, Chen Wang, Qiwei Han et al.

The integration of voice-based AI agents in healthcare presents a transformative opportunity to bridge economic and accessibility gaps in digital health delivery. This paper explores the role of large language model (LLM)-powered voice assistants in enhancing preventive care and continuous patient monitoring, particularly in underserved populations. Drawing insights from the development and pilot study of Agent PULSE (Patient Understanding and Liaison Support Engine) -- a collaborative initiative between IBM Research, Cleveland Clinic Foundation, and Morehouse School of Medicine -- we present an economic model demonstrating how AI agents can provide cost-effective healthcare services where human intervention is economically unfeasible. Our pilot study with 33 inflammatory bowel disease patients revealed that 70\% expressed acceptance of AI-driven monitoring, with 37\% preferring it over traditional modalities. Technical challenges, including real-time conversational AI processing, integration with healthcare systems, and privacy compliance, are analyzed alongside policy considerations surrounding regulation, bias mitigation, and patient autonomy. Our findings suggest that AI-driven voice agents not only enhance healthcare scalability and efficiency but also improve patient engagement and accessibility. For healthcare executives, our cost-utility analysis demonstrates huge potential savings for routine monitoring tasks, while technologists can leverage our framework to prioritize improvements yielding the highest patient impact. By addressing current limitations and aligning AI development with ethical and regulatory frameworks, voice-based AI agents can serve as a critical entry point for equitable, sustainable digital healthcare solutions.

Alessandro Gambetti, Qiwei Han

Online reviews in the form of user-generated content (UGC) significantly impact consumer decision-making. However, the pervasive issue of not only human fake content but also machine-generated content challenges UGC's reliability. Recent advances in Large Language Models (LLMs) may pave the way to fabricate indistinguishable fake generated content at a much lower cost. Leveraging OpenAI's GPT-4-Turbo and DALL-E-2 models, we craft AiGen-FoodReview, a multi-modal dataset of 20,144 restaurant review-image pairs divided into authentic and machine-generated. We explore unimodal and multimodal detection models, achieving 99.80% multimodal accuracy with FLAVA. We use attributes from readability and photographic theories to score reviews and images, respectively, demonstrating their utility as hand-crafted features in scalable and interpretable detection models, with comparable performance. The paper contributes by open-sourcing the dataset and releasing fake review detectors, recommending its use in unimodal and multimodal fake review detection tasks, and evaluating linguistic and visual features in synthetic versus authentic data.

Erik Fubel, Niclas Michael Groll, Patrick Gundlach et al.

Search Engine Result Pages (SERPs) serve as the digital gateways to the vast expanse of the internet. Past decades have witnessed a surge in research primarily centered on the influence of website ranking on these pages, to determine the click-through rate (CTR). However, during this period, the landscape of SERPs has undergone a dramatic evolution: SERP features, encompassing elements such as knowledge panels, media galleries, FAQs, and more, have emerged as an increasingly prominent facet of these result pages. Our study examines the crucial role of these features, revealing them to be not merely aesthetic components, but strongly influence CTR and the associated behavior of internet users. We demonstrate how these features can significantly modulate web traffic, either amplifying or attenuating it. We dissect these intricate interaction effects leveraging a unique dataset of 67,000 keywords and their respective Google SERPs, spanning over 40 distinct US-based e-commerce domains, generating over 6 million clicks from 24 million views. This cross-website dataset, unprecedented in its scope, enables us to assess the impact of 24 different SERP features on organic CTR. Through an ablation study modeling CTR, we illustrate the incremental predictive power these features hold.

Max Würfel, Qiwei Han, Maximilian Kaiser

Online advertising revenues account for an increasing share of publishers' revenue streams, especially for small and medium-sized publishers who depend on the advertisement networks of tech companies such as Google and Facebook. Thus publishers may benefit significantly from accurate online advertising revenue forecasts to better manage their website monetization strategies. However, publishers who only have access to their own revenue data lack a holistic view of the total ad market of publishers, which in turn limits their ability to generate insights into their own future online advertising revenues. To address this business issue, we leverage a proprietary database encompassing Google Adsense revenues from a large collection of publishers in diverse areas. We adopt the Temporal Fusion Transformer (TFT) model, a novel attention-based architecture to predict publishers' advertising revenues. We leverage multiple covariates, including not only the publisher's own characteristics but also other publishers' advertising revenues. Our prediction results outperform several benchmark deep-learning time-series forecast models over multiple time horizons. Moreover, we interpret the results by analyzing variable importance weights to identify significant features and self-attention weights to reveal persistent temporal patterns.

Joel Peito, Qiwei Han

In contrast to many other domains, recommender systems in health services may benefit particularly from the incorporation of health domain knowledge, as it helps to provide meaningful and personalised recommendations catering to the individual's health needs. With recent advances in representation learning enabling the hierarchical embedding of health knowledge into the hyperbolic Poincare space, this work proposes a content-based recommender system for patient-doctor matchmaking in primary care based on patients' health profiles, enriched by pre-trained Poincare embeddings of the ICD-9 codes through transfer learning. The proposed model outperforms its conventional counterpart in terms of recommendation accuracy and has several important business implications for improving the patient-doctor relationship.

Qiwei Han, Mengxin Ji, Inigo Martinez de Rituerto de Troya et al.

We partner with a leading European healthcare provider and design a mechanism to match patients with family doctors in primary care. We define the matchmaking process for several distinct use cases given different levels of available information about patients. Then, we adopt a hybrid recommender system to present each patient a list of family doctor recommendations. In particular, we model patient trust of family doctors using a large-scale dataset of consultation histories, while accounting for the temporal dynamics of their relationships. Our proposed approach shows higher predictive accuracy than both a heuristic baseline and a collaborative filtering approach, and the proposed trust measure further improves model performance.