An Adaptive AI Model for Intelligent Fraud Detection and Customer Engagement in Digital Banking
Bibliographic record
Abstract
Digital banking has transformed financial accessibility while concurrently heightening clients' exposure to fraud threats and reducing personal user experiences. Conventional fraud detection techniques frequently struggle to adjust to changing attack vectors, while consumer interaction strategies lack in personalisation and real-time reactivity. This research introduces an adaptable AI system that integrates a Long Short-Term Memory (LSTM) network with Gradient Boosted Decision Trees (GBDT) for fraud detection, with a reinforcement learning module for enhanced customer engagement. This dual-module system utilises real-world transaction datasets from Kaggle, employing advanced feature engineering, concept drift adaptability, and sentiment-aware personalisation. The suggested approach markedly outperformed baseline models, including Logistic Regression, Random Forest, and XGBoost, in fraud detection, attaining a precision of 0.98, recall of 0.96, F1-score of 0.97, and AUC-ROC of 0.99. These measures confirm the strength and dependability of the system in complex financial contexts. The engagement module enhanced response and conversion rates by dynamically customising interactions according to user behaviour and sentiment analysis. This integrated and flexible model strengthens security and improves the digital banking experience compared to previous alternatives. The findings indicate significant improvements over traditional methods, offering a thorough answer to current digital banking issues.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".