Unsupervised Deep Learning for Credit Card Fraud Detection: An Autoencoder-Driven Framework with Real-Time Dash Visualization Using Tensorflow 2.X
Bibliographic record
Abstract
The exponential growth in digital transactions has escalated the need for intelligent, real-time fraud detection mechanisms capable of handling high-volume, imbalanced datasets. This paper presents an unsupervised deep learning framework for credit card fraud detection using autoencoders, specifically tailored to isolate anomalous behavior without relying on labeled fraudulent data. The architecture leverages TensorFlow 2.x for model development, training, and evaluation, enabling precise identification of outliers within complex transactional patterns. The system incorporates a comprehensive data preprocessing pipeline using Pandas and NumPy to normalize, encode, and balance transaction records for optimized model performance. Post-training, the model is integrated with an interactive Python Dash-based dashboard, facilitating real-time visualization of anomaly scores and system metrics for analysts and security teams. The proposed solution emphasizes scalability, interpretability, and responsiveness, supporting deployment in high-throughput environments. Experimental validation on publicly available datasets demonstrates high reconstruction error sensitivity, achieving competitive performance in terms of precision and recall. This research underscores the effectiveness of autoencoder-based anomaly detection in financial fraud scenarios and contributes a modular, production-ready framework for organizations seeking to enhance digital transaction security through data-driven intelligen ce
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".