Fraud in financial services—especially account opening fraud—poses major operational and reputational risks. Static rules struggle to adapt to evolving tactics, missing novel patterns and generating excessive false positives. Machine learning promises adaptive detection, but deployment faces severe class imbalance: in the NeurIPS 2022 BAF Base benchmark used here, fraud prevalence is 1.10%. Standard metrics (accuracy, f1_weighted) can look strong while doing little for the minority class. We compare Logistic Regression, SVM (RBF), Random Forest, LightGBM, and a GRU model on N = 1,000,000 accounts under a unified preprocessing pipeline. All models are trained to minimize their loss function, while configurations are selected on a stratified development set using validation-weighted F1-score f1_weighted. For the four classical models, class weighting in the loss (class_weight $\in \{\mathrm{None},‘\mathrm{balanced}’\}$) is treated as a hyperparameter and tuned. Similarly, the GRU is trained with a fixed class-weighted CrossEntropy loss that up-weights fraud cases. This ensures that both model families leverage weighted training objectives, while their final hyperparameters are consistently selected by the f1_weighted metric. Despite similar AUCs and aligned feature importance across families, the classical models converge to high-precision, low-recall solutions (1–6% fraud recall), whereas the GRU recovers 78% recall at 5% precision (AUC $=0.8800$). Under extreme imbalance, objective choice and operating point matter at least as much as architecture.

Detecting fake news is a critical challenge in natural language processing (NLP), demanding solutions that balance accuracy, interpretability, and computational efficiency. Despite advances in NLP, systematic empirical benchmarks that directly compare both classical and deep models—across varying input richness and with careful attention to interpretability and computational tradeoffs—remain underexplored. In this study, we systematically evaluate the mathematical foundations and empirical performance of five representative models for automated fake news classification: three classical machine learning algorithms (Logistic Regression, Random Forest, and Light Gradient Boosting Machine) and two state-of-the-art deep learning architectures (A Lite Bidirectional Encoder Representations from Transformers—ALBERT and Gated Recurrent Units—GRUs). Leveraging the large-scale WELFake dataset, we conduct rigorous experiments under both headline-only and headline-plus-content input scenarios, providing a comprehensive assessment of each model’s capability to capture linguistic, contextual, and semantic cues. We analyze each model’s optimization framework, decision boundaries, and feature importance mechanisms, highlighting the empirical tradeoffs between representational capacity, generalization, and interpretability. Our results show that transformer-based models, especially ALBERT, achieve state-of-the-art performance (macro F1 up to 0.99) with rich context, while classical ensembles remain viable for constrained settings. These findings directly inform practical fake news detection.

Fraud in financial services—especially account opening fraud—poses major operational and reputational risks. Static rules struggle to adapt to evolving tactics, missing novel patterns and generating excessive false positives. Machine learning promises adaptive detection, but deployment faces severe class imbalance: in the NeurIPS 2022 BAF Base benchmark used here, fraud prevalence is 1.10%. Standard metrics (accuracy, f1_weighted) can look strong while doing little for the minority class. We compare logistic regression, SVM (RBF), Random Forest, LightGBM, and a GRU model on N=1,000,000 accounts under a unified preprocessing pipeline. All models are trained to minimize their loss function, while configurations are selected on a stratified development set using validation 1_weighted. For the four classical models, class weighting in the loss (class_weight in {None, 'balanced'}) is treated as a hyperparameter and tuned. Similarly, the GRU is trained with a fixed class-weighted cross-entropy loss that up-weights fraud cases. This ensures that both model families leverage weighted training objectives, while their final hyperparameters are consistently selected by the f1_weighted metric. Despite similar AUCs and aligned feature importance across families, the classical models converge to high-precision, low-recall solutions (1-6% fraud recall), whereas the GRU recovers 78% recall at 5% precision (AUC = 0.8800). Under extreme imbalance, objective choice and operating point matter at least as much as architecture.

The automated detection of hate speech is a critical but difficult task due to its subjective, behavior-driven nature, which leads to frequent annotator disagreement. While advanced models (e.g., transformers) are state-of-the-art, it is unclear how their performance is affected by the methodological choice of label aggregation (e.g., majority vote vs. unanimous agreement) and task complexity. We conduct a 2x2 quasi-experimental study to measure the compounding impact of these two factors: Labeling Strategy (low-ambiguity ``Pure'' data vs. high-ambiguity ``Majority'' data) and Task Granularity (Binary vs. Multi-class). We evaluate five models (Logistic Regression, Random Forest, Light Gradient Boosting Machine [LightGBM], Gated Recurrent Unit [GRU], and A Lite BERT [ALBERT]) across four quadrants derived from the HateXplain dataset. We find that (1) ALBERT is the top-performing model in all conditions, achieving its peak F1-Score (0.8165) on the ``Pure'' multi-class task. (2) Label ambiguity is strongly associated with performance loss; ALBERT's F1-Score drops by $\approx$15.6\% (from 0.8165 to 0.6894) when trained on the higher-disagreement ``Majority'' data in the multi-class setting. (3) This negative effect is compounded by task complexity, with the performance drop being nearly twice as severe for the multi-class task as for the binary task. A sensitivity analysis confirmed this drop is not an artifact of sample size. We conclude that in HateXplain, behavioral label ambiguity is a more significant bottleneck to model performance than model architecture, providing strong evidence for a data-centric approach.

Spam on messaging apps like Telegram is a serious threat to user security andexperience. In this paper, we compared several machine learning (ML) and deep learning (DL)models to find the most effective way to detect it. We tested our models on a dataset of 20,348messages. We put classic approaches like Logistic Regression and Tree-based Modelsincluding bagging and boosting against modern neural networks—a GRU and the ALBERTtransformer. The results demonstrate that both GRU and ALBERT were the clear winners. TheALBERT model was the top performer, achieving state-of-the-art results with a weightedF1-score of 0.97 and an AUC of 0.9943. The GRU model also delivered excellent performance,with an F1-score of 0.94. Their real strength was in identifying the tricky minority ‘spam’class. Here, ALBERT reached an F1-score of 0.95, and the GRU model scored 0.90,significantly outperforming the other methods. We used McNemar's test to confirm thesefindings were statistically significant. Ultimately, our study sets a new benchmark for spamdetection. It proves that transformer models can effectively secure messaging platforms usingonly the content of the message itself.