Money Laundering Detection with AI

A method for detecting anomalous activity, like fraud or money laundering, using a dynamic approach that combines transaction analysis and social network analysis. The method involves calculating anomaly scores for user transactions using unsupervised and supervised algorithms trained on transaction attributes. It also calculates network anomaly scores based on interconnected user profiles. The potential for anomalous activity is determined by combining the transaction and network scores. This provides dynamic detection from multiple angles rather than just transaction analysis alone.

Source

Secure electronic financial transactions system that uses AI, biometrics, and multimodal data analysis to prevent fraud and improve user experience. The system collects multimodal data from visual, auditory, and tactile sensors during transactions. It uses AI modules like biometric authentication, transaction anomaly detection, geospatial analysis, behavioral analysis, and third-party data integration to analyze this data for fraud prevention. The system also communicates with users through modalities like vision, audio, touch, taste, smell, temperature, pain, and balance to address fraud concerns or request verification.

Source

Anti-money laundering suspicious transaction monitoring system that uses real-time collection of transaction and personal data to improve accuracy and reduce false positives compared to just relying on bank transaction data. The system collects details like account balances, property, assets, insurance, and income for monitored individuals. It associates this with their basic info and continuously monitors for suspicious activity. This comprehensive data allows more accurate detection of money laundering beyond just bank transactions.

Source

Anti-money laundering suspicious transaction identification method and device that combines rule-based and machine learning models to improve accuracy and coverage compared to using just one approach. The method involves using a rule model and a machine learning model in parallel, weighting their results, and using the weighted average to determine if a transaction is suspicious. The models are iteratively trained with updated data to keep up with evolving money laundering techniques.

Source

Determining the likelihood of a connection between funds entering and exiting a cryptocurrency tumbler, to identify laundered funds. The method involves using classical computers to formulate an optimization problem representing the tumbler's flows. This is converted to a quantum-computable quadratic unconstrained binary optimization (QUBO) form. A quantum computer solves the QUBO to find matrices representing the tumbler's internal flows. Classical post-processing generates a probability matrix showing likelihoods of connections between input and output funds.

Source

Detecting money laundering activities hidden in large volumes of legitimate transactions using neural networks to compare financial transaction patterns. The method involves generating target and baseline vectors representing transaction activity for a specific party and overall region, respectively. A Siamese neural network compares the vectors to detect deviations indicative of potential money laundering. A drift score between the vectors is calculated, constrained in a learned space between non-money laundering and money laundering transactions. An alarm is triggered if the drift score indicates potential money laundering.

Source

An anti-money laundering (AML) suspicious transaction identification method using reinforcement learning to improve coverage and accuracy compared to traditional methods like rule engines and supervised learning. The method involves using reinforcement learning to train a model that takes customer and environmental data as input and outputs whether the transaction is suspicious for money laundering. The model learns by minimizing loss based on true labels, allowing it to adapt to changing risks and respond faster than offline training. The method involves obtaining transaction data, generating a state vector, training a loss prediction network, selecting actions using a search strategy, and updating parameters based on true labels.

Source

System for more effectively and efficiently identifying potentially suspicious cash structuring activity that may be related to money laundering or other financial crimes. The system uses a deep learning model with convolutional layers and non-linear activation functions to analyze daily transaction patterns and global transaction patterns separately. It extracts daily patterns from the daily transactions, aggregates them, and combines them with global transaction patterns. This aggregated input is fed into a classifier to generate scores for the account. If the score exceeds a threshold, it alerts for potential suspicious activity. The model uses techniques like dilated convolutions, L2 weight decay, Adam optimization, and ensemble teacher distillation to improve performance.

Source

Identifying suspicious activity using a multidimensional approach that goes beyond just transaction data to improve accuracy and adaptability compared to existing systems. The method involves preprocessing monitoring data using a plurality of vectors, applying rules to each vector, and triggering actions based on the rules. The vectors capture context beyond just transactions, such as party details, location, etc. This multidimensional approach allows identifying suspicious activity that would be missed by single-dimensional transaction-only analysis.

Source

Money laundering structure detection using hypergraph heterogeneous graph hierarchical representation learning to improve accuracy and applicability of existing technology for detecting money laundering structures. The method involves modeling transaction networks as heterogeneous graphs with meta-paths representing money laundering scenarios. Heterogeneous graph hierarchical representation learning is used to mine structure features from transaction, user, and association layers. This hierarchical representation greatly improves money laundering structure detection compared to homogeneous network methods.

Source

Automatically detecting suspicious money laundering transactions using artificial intelligence models. The method involves using two AI models - one to identify transactions as potential money laundering targets, and another to score the likelihood of money laundering. Transactions flagged by the first model are further analyzed by the second model to determine a suspicion level. If the level exceeds a threshold, the transaction is reported as suspicious. The AI models are trained using financial transaction data to learn patterns indicative of money laundering.

Source

Using AI to predict the growth of money laundering networks in financial systems and prioritize action against them. The method involves monitoring networks already identified as potential money laundering networks, predicting their future growth size based on past changes, and prioritizing networks with high growth potential for intervention. The prediction is done using AI models on historical network data.

Source

Using machine learning to improve anti-money laundering (AML) analysis by accurately identifying accounts and account holders with money laundering risk. The method involves obtaining a dataset of accounts and applying a trained algorithm to generate money laundering risk scores for each account holder. Accounts with high risk scores are flagged for investigation. The algorithm uses a dataset of aggregated financial data from multiple sources to analyze account variables like transactions, characteristics, and relationships. It provides actionable recommendations and prioritization for compliance teams.

Source

Tree-based user identification for real-time anti-money laundering monitoring. The method involves using tree models, like decision trees, to identify potential money laundering activities in real-time transactions. It leverages offline daily models trained on historical data to predict money laundering risks for users. This daily model identifies high-risk users for review. The daily model's feature importance is used to build a lightweight real-time model that can quickly identify potential money laundering in real-time transactions. The real-time model is more lightweight and fast compared to the daily model due to feature selection.

Source

Machine learning techniques for reviewing alerts in regulatory settings like anti-money laundering (AML) that provide insights and a flexible interface to improve efficiency and accuracy. The techniques involve calculating context-aware representations of entities like customers and transactions using self-supervised graph neural networks. These representations can be used to derive insights like clustering, anomaly scoring, and period detection to aid in AML alert review. The representations capture entity behavior based on surrounding context from a bipartite graph.

Source

Using machine learning to identify potential criminal activity involving financial institutions' customers by analyzing news alerts. The method involves extracting entities from news alerts, resolving them to known customers, enriching the alerts with customer data, predicting the likelihood of a suspicious activity report, and transmitting the enriched alerts to the appropriate investigator.

Source

Improving anti-money laundering detection by identifying money laundering rings instead of just individual accounts. The method involves clustering accounts based on their transaction behavior, then identifying money laundering gangs among the clusters. This leverages group-level transaction patterns to improve detection accuracy compared to analyzing accounts independently.

Source

Detecting financial crimes like money laundering using machine learning models that leverage network effects between financial entities. The method involves generating network features by applying risk indicators to a graph model of financial entities and their relationships. These network features are fed into machine learning models trained on both network and non-network features to predict financial crimes. Alerts are generated when crimes are predicted, identifying the involved entities. The network representation helps reveal hidden connections and improve crime detection compared to traditional non-network features.

Source

Detecting fraud in financial networks without relying on hardcoded rules by using graph neural networks to identify suspicious transaction patterns. The method involves generating a transaction graph representing the financial network with synthetic suspect transactions. Subgraphs are extracted and used to train a graph neural network model to classify subgraphs as suspect. This model is then applied to new financial networks to locate potentially fraudulent transaction patterns. The subgraph extraction dynamically selects nodes based on their transaction history to capture related activity.

Source

Anti-money laundering (AML) identification method, device, system and medium based on fusion models that combines decision models and feature extraction models to improve AML detection accuracy and efficiency. The method involves preprocessing transaction samples, extracting features, screening important variables using a decision model, and feeding them to a feature extraction model for AML classification. This fusion approach allows automated identification without manual screening.

Source