Personal Banking using AI

Providing personalized financial insights to individuals based on comparative analysis of their investment profiles with similar users. The method involves training a machine learning model to process investment data of multiple users and predict investment percentages for categories. When a user accesses a banking platform, their investment profile is compared using the model to find similar users. Results from their analysis are displayed to the user. The comparative analysis helps users see how their investment choices compare to peers with similar attributes.

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

Automated financial guidance system that provides personalized financial advice to individuals based on their financial data. The system uses a guidance engine that analyzes a user's financial accounts and provides concrete, personalized steps to becoming more financially healthy. It takes inputs like income, expenses, debt, and savings, optimizes and integrates the data, and then recommends actions based on a financial best practices standard. The engine categorizes users based on emergency fund and high interest debt levels to determine next steps. Confidence scores quantify accuracy.

Source

Dynamic payment switching system that allows optimizing outgoing payments based on user intent instead of just selecting from a fixed menu. The system presents features like speed, cost, recallability, etc. to the payor. They select a subset, indicating their payment intent. The system then chooses an appropriate payment mechanism that matches that intent. This allows separating user preferences from mechanism selection. It can provide better overall payment experience by customizing the mechanism to meet the user's desired tradeoff between speed, cost, etc.

Source

Enhanced asset transfer using voice analysis and optical recognition to simplify and streamline moving financial assets between institutions. It involves converting customer requests to transfer assets between banks into fractional NFTs (F-NFTs) using voice analysis. These F-NFTs are then traded on an NFT exchange. The process uses voice recognition to extract asset transfer details, creates F-NFTs representing the assets, and transfers them through the exchange. An optical receptive net is also used to accurately reconcile and extract features from documents for better document processing. This allows efficient, real-time, and end-to-end tracking of asset transfers between institutions using voice input and optical recognition.

Source

Dynamic modeling system for credit scoring that uses machine learning and real-time credit value modeling to provide customized credit options and conditions for users. The system generates user interface elements that dynamically present account-specific credit values and conditions based on user activity and risk analysis. It uses an activity machine learning model to calculate a risk score from user activity data, then a credit value model to determine dynamic credit ranges and conditions for selected credit values. This allows flexible, efficient, and accurate presentation of customized credit options and conditions tailored to each user's activity level and risk profile.

Source

Contact-minimized automated teller machine (ATM) using radar-based gesture recognition and authentication to eliminate the need for physical cards and keypads. The ATM has a radar transmitter to create a field in front of it. Customers interact with the ATM using gestures instead of touching buttons or cards. The radar detects the gestures and translates them into actions. The ATM can also identify customers based on unique gestures learned during account setup. This provides contactless ATM usage and reduces transmission of germs.

Source

Controlled prioritization of transactions to prevent overdrafts and late payments using AI. The system predicts future transactions based on historical data, assigns priority scores, and approves/denies them based on account balance. This prevents approving low priority transactions that could leave insufficient funds for high priority ones. It uses AI to analyze transaction history, predict future transactions, and score them for prioritization. This allows approving/denying transactions based on balance and priority instead of just following scheduling.

Source

Improving commercial communications and preventing overdrafts using cognitive computing in banking. The system uses machine learning and predictive modeling to analyze user data and detect when a user is likely to overdraft their account. When a user is near a store and predicted to spend more than their balance, the system notifies them. It also transfers funds between accounts to optimize interest. The system generates shopping profiles to deliver targeted offers to preferred vendors when users are near.

Source

Modular system for personalized financial planning and advice using user profiles. The system receives a user profile with goals and characteristics, selects appropriate financial approach blocks based on the profile, and generates a customized financial plan for the user. This allows tailored financial guidance and planning that considers individual factors beyond generic advice. The system uses machine learning models to determine personalized financial health scores and predictions.

Source

Artificial intelligence-based financial management system that provides personalized debt management recommendations to consumers based on their preferences and spending patterns. The system categorizes a user's transactions, lets them select financial and transaction preferences, trains a machine learning model on those preferences, calculates the influence of actions on preferences, filters actions with positive influence, ranks them, and recommends the best one to the user. The recommendations are presented via notifications on their device.

Source

Predicting financial well-being of individuals without requiring them to complete surveys, using machine learning models trained on personal data. The models learn to correlate personal data sets of users with their assessment scores. To predict a user's score, the model matches their personal data to that of other users. If a difference between predicted and test scores exceeds a threshold, actions are taken like sending communications or changing account settings. The models use unsupervised learning on user data sets without labels.

Source

Predicting financial wellness scores for users without requiring them to complete surveys. The method involves training a machine learning model using unsupervised learning on personal data sets from multiple users. The model correlates personal data from a new user to the data sets of existing users. It then predicts their financial wellness scores without needing them to fill out surveys. The model can also intervene to improve scores based on the predictions.

Source

Using machine learning to predict financial wellness scores for individuals without requiring them to complete surveys. The method involves training a machine learning model using personal data from a set of users. The model predicts financial wellness scores for new users based on correlating their personal data to the training set. Changes in predicted scores indicate potential events like relationship changes. The model can also send notifications about these events. By leveraging existing user data, the model can provide timely financial wellness insights without requiring repeated surveys.

Source

Enabling users to schedule payments using voice or text commands through a payment app, without needing to navigate complex menus or remember OTPs. The app extracts payment instructions from natural language input and authenticates the user based on factors like location, facial features, typing patterns, etc. This allows scheduling payments using conversational commands like "Pay my credit card bill on Thursday" or "Send $50 to Mom next week". The app encrypts the instruction and factors and sends to the server, which processes the scheduled payment. This provides an intuitive and convenient way to schedule payments using natural language input and automatic authentication.

Source

Generating a personalized pecuniary program using machine learning to optimize financial goals and behavior based on a user's financial trends. The system retrieves financial data for a user, identifies trends, and classifies them using a trained machine learning model. It then generates a customized financial program tailored to the priority scores assigned to the trends. By continuously learning and adapting based on the user's financial history, it aims to improve financial management and goal attainment.

Source

Using machine learning to improve user authentication in financial transactions by generating more effective challenge questions that are tailored to the specific transactions of an authorized user. The method involves training a machine learning model to identify financial transactions that an authorized user is likely to remember based on their transaction history. This allows generating challenge questions about recent transactions that are more likely to be answered correctly by the authorized user.

Source

Automatically reconciling bank statements using machine learning to suggest account matches for transactions. The method involves identifying features like transaction description, payee name, and account for previously reconciled transactions. A machine learning model is trained with this data. When a new statement transaction is received, the model suggests reconciliations based on the features. High confidence suggestions are presented, and lower confidence suggestions require manual reconciliation. The model can also be customized for individual entities by training it with their specific transaction history.

Source

Automatically implementing personalized financial advice for users based on machine learning and comparison with financial peers. The system receives historic transactions from multiple financial institutions, identifies unexpected expenses, creates savings plans, and automatically transfers funds to account for them. It also identifies recurring transactions, schedules payments, categorizes transactions, allows hierarchy adjustment, and creates a financial plan based on machine learning and user goals. By leveraging machine learning and peer comparison, it aims to provide more practical and actionable financial advice compared to conventional systems.

Source

Hybrid pipeline for accurately predicting customer IDs from bank statements using a combination of lookup tables and deep learning models. The pipeline receives a bank statement, looks up the statement's key in a table to find matching customer IDs, and uses a DL model if the key isn't found. This leverages the fact that payments from the same account should have the same customer ID. The pipeline improves accuracy compared to relying solely on the DL model.

Source