Search

The volume of e-commerce continues to increase year after year. Buying goods on the internet is easy and practical, and took a huge boost during the lockdowns of the Covid crisis. However, this is also an open window for fraudsters and the corresponding financial loss costs billions of dollars. In this paper, we study e-commerce credit card fraud detection, in collaboration with our industrial partner, Worldline. Transactional companies are more and more dependent on machine learning models such as deep learning anomaly detection models, as part of real-world fraud detection systems (FDS). We focus on continual learning to find the best model with respect to two objectives: to maximize the accuracy and to minimize the catastrophic forgetting phenomenon. For the latter, we proposed an evaluation procedure to quantify the forgetting in data streams with delayed feedback: the plasticity/stability visualization matrix. We also investigated six strategies and 13 methods on a real-size case study including five months of e-commerce credit card transactions. Finally, we discuss how the trade-off between plasticity and stability is set, in practice, in the case of FDS., SCOPUS: ar.j, info:eu-repo/semantics/published

In recent years, numerous embedding models have been made available and widely used for various NLP tasks. Choosing a model that performs well for several tasks in English has been largely simplified by the Massive Text Embedding Benchmark (MTEB), but extensions to other languages remain challenging. This is why we expand MTEB to propose the first massive benchmark of sentence embeddings for French. Not only we gather 22 existing datasets in an easy-to-use interface, but we also create three new French datasets for a global evaluation over 8 different tasks. We perform a large scale comparison with 46 carefully selected embedding models, conduct comprehensive statistical tests, and analyze the correlation between model performance and many of their characteristics. We find out that even if no model is the best on all tasks, large multilingual models pre-trained on sentence similarity perform particularly well. Our work comes with open-source code, new datasets and a public leaderboard.

Fraud detection systems (FDS) mainly perform two tasks: (i) real-time detection while the payment is being processed and (ii) posterior detection to block the card retrospectively and avoid further frauds. Since human verification is often necessary and the payment processing time is limited, the second task manages the largest volume of transactions. In the literature, fraud detection challenges and algorithms performance are widely studied but the very formulation of the problem is never disrupted: it aims at predicting if a transaction is fraudulent based on its characteristics and the past transactions of the cardholder. Yet, in posterior detection, verification often takes days, so new payments on the card become available before a decision is taken. This is our motivation to propose a new paradigm: posterior fraud detection with "future" information. We start by providing evidence of the on-time availability of subsequent transactions, usable as extra context to improve detection. We then design a Bidirectional LSTM to make use of these transactions. On a real-world dataset with over 30 million transactions, it achieves higher performance than a regular LSTM, which is the state-of-the-art classifier for fraud detection that only uses the past context. We also introduce new metrics to show that the proposal catches more frauds, more compromised cards, and based on their earliest frauds. We believe that future works on this new paradigm will have a significant impact on the detection of compromised cards., Comment: 11 pages, 4 figures, to be published at AISTATS 2022

The dark face of digital commerce generalization is the increase of fraud attempts. To prevent any type of attacks, state-of-the-art fraud detection systems are now embedding Machine Learning (ML) modules. The conception of such modules is only communicated at the level of research and papers mostly focus on results for isolated benchmark datasets and metrics. But research is only a part of the journey, preceded by the right formulation of the business problem and collection of data, and followed by a practical integration. In this paper, we give a wider vision of the process, on a case study of transfer learning for fraud detection, from business to research, and back to business.

The dark face of digital commerce generalization is the increase of fraud attempts. To prevent any type of attacks, state-of-the-art fraud detection systems are now embedding Machine Learning (ML) modules. The conception of such modules is only communicated at the level of research and papers mostly focus on results for isolated benchmark datasets and metrics. But research is only a part of the journey, preceded by the right formulation of the business problem and collection of data, and followed by a practical integration. In this paper, we give a wider vision of the process, on a case study of transfer learning for fraud detection, from business to research, and back to business.

Every second, thousands of credit or debit card transactions are processed in financial institutions. This extensive amount of data and its sequential nature make the problem of fraud detection particularly challenging. Most analytical strategies used in production are still based on batch learning, which is inadequate for two reasons: Models quickly become outdated and require sensitive data storage. The evolving nature of bank fraud enshrines the importance of having up-to-date models, and sensitive data retention makes companies vulnerable to infringements of the European General Data Protection Regulation. For these reasons, evaluating incremental learning strategies is recommended. This paper designs and evaluates incremental learning solutions for real-world fraud detection systems. The aim is to demonstrate the competitiveness of incremental learning over conventional batch approaches and, consequently, improve its accuracy employing ensemble learning, diversity and transfer learning. An experimental analysis is conducted on a full-scale case study including five months of e-commerce transactions and made available by our industry partner, Worldline., SCOPUS: ar.j, info:eu-repo/semantics/published

The dark face of digital commerce generalization is the increase of fraud attempts. To prevent any type of attacks, state-of-the-art fraud detection systems are now embedding Machine Learning (ML) modules. The conception of such modules is only communicated at the level of research and papers mostly focus on results for isolated benchmark datasets and metrics. But research is only a part of the journey, preceded by the right formulation of the business problem and collection of data, and followed by a practical integration. In this paper, we give a wider vision of the process, on a case study of transfer learning for fraud detection, from business to research, and back to business.

Open Domain Question Answering (ODQA) on a large-scale corpus of documents (e.g. Wikipedia) is a key challenge in computer science. Although transformer-based language models such as Bert have shown on SQuAD the ability to surpass humans for extracting answers in small passages of text, they suffer from their high complexity when faced to a much larger search space. The most common way to tackle this problem is to add a preliminary Information Retrieval step to heavily filter the corpus and only keep the relevant passages. In this paper, we propose a more direct and complementary solution which consists in applying a generic change in the architecture of transformer-based models to delay the attention between subparts of the input and allow a more efficient management of computations. The resulting variants are competitive with the original models on the extractive task and allow, on the ODQA setting, a significant speedup and even a performance improvement in many cases.

Recent advances with language models (e.g. BERT, XLNet, ...), have allowed surpassing human performance on complex NLP tasks such as Reading Comprehension. However, labeled datasets for training are available mostly in English which makes it difficult to acknowledge progress in other languages. Fortunately, models are now pre-trained on unlabeled data from hundreds of languages and exhibit interesting transfer abilities from one language to another. In this paper, we show that multilingual BERT is naturally capable of zero-shot transfer for an extractive Question Answering task (eQA) from English to other languages. More specifically, it outperforms the best previously known baseline for transfer to Japanese and French. Moreover, using a recently published large eQA French dataset, we are able to further show that (1) zero-shot transfer provides results really close to a direct training on the target language and (2) combination of transfer and training on target is the best option overall. We finally present a practical application: a multilingual conversational agent called Kate which answers to HR-related questions in several languages directly from the content of intranet pages.

Machine learning models deployed in real-world applications are often evaluated with precision-based metrics such as F1-score or AUC-PR (Area Under the Curve of Precision Recall). Heavily dependent on the class prior, such metrics make it difficult to interpret the variation of a model's performance over different subpopulations/subperiods in a dataset. In this paper, we propose a way to calibrate the metrics so that they can be made invariant to the prior. We conduct a large number of experiments on balanced and imbalanced data to assess the behavior of calibrated metrics and show that they improve interpretability and provide a better control over what is really measured. We describe specific real-world use-cases where calibration is beneficial such as, for instance, model monitoring in production, reporting, or fairness evaluation., Comment: Presented at IDA2020

This paper presents a new interactive opinion mining tool that helps users to classify large sets of short texts originated from Web opinion polls, technical forums or Twitter. From a manual multi-label pre-classification of a very limited text subset, a learning algorithm predicts the labels of the remaining texts of the corpus and the texts most likely associated to a selected label. Using a fast matrix factorization, the algorithm is able to handle large corpora and is well-adapted to interactivity by integrating the corrections proposed by the users on the fly. Experimental results on classical datasets of various sizes and feedbacks of users from marketing services of the telecommunication company Orange confirm the quality of the obtained results., Comment: 8 pages