AI-Powered Personal Banking

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

Personalized bank asset management using AI to provide tailored investment strategies and services to customers based on their behavior, risk tolerance, and preferences. The method involves analyzing a customer's historical bank financial data to understand their assets, transactions, and cognitive biases. This data is used to generate a personalized portfolio, product recommendations, and investment simulation. The simulation is evaluated and optimized based on customer goals and risk tolerance. The AI model then provides customized asset management services.

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

Bank customer classification method that uses machine learning and multiple channel data integration to accurately and efficiently segment bank customers based on their needs and behaviors. The method involves formulating classification goals, collecting customer data from multiple channels, determining key indicators, using machine learning to identify patterns, designing customized classification methods, and developing personalized service strategies for each segment.

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

Bank product recommendation system that uses machine learning to provide personalized product recommendations to bank customers based on their similarities to other customers. The system extracts user features from basic information, finds similar users, and recommends products they interacted with. It also extracts product features using a dual-stream model with text and image embeddings. This allows leveraging both text and images in product descriptions for recommendations. The system trains the product feature model using triplet samples to converge the loss function.

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

Recommending financial products to customers that are more in line with their preferences and the bank's interests. The method combines historical purchase records, bank product data, and interest rate predictions to avoid inaccurate customer information and select products beneficial to the bank. It finds financial products that the same customer bought, calculates recommendation scores based on product associations and interest rates, then selects products with high support, confidence, and recommendation.

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

A customer service and marketing management system for the financial industry that uses data analysis and personalization to improve user experience and product recommendations. The system has modules for user management, financial product matching, user interaction, and product demand navigation. It collects user data passively, analyzes user needs, recommends suitable products, provides personalized interactions, and navigates users to their demanded products. This improves the accuracy and effectiveness of user targeting, product matching, and marketing.

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

Intelligent regulation of financial resources to tilt them towards better customers in internet finance. It involves predicting customer behavior after handling financial services, evaluating customers based on predictions, and adjusting financial attribute data in processing strategies based on evaluations. This aims to make financial resources more likely to go to high-quality customers, increasing activity and reducing risk.

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

An interactive annuity product design using machine learning to provide customizable annuities with transparent fees and flexible risk management. The system generates annuity recommendations and simulations based on user preferences and market predictions. It leverages machine learning to optimize annuity products for users' objectives and risk profiles. Users can select from a range of investment options and risk levels. The system provides transparent pricing for customized risk management options.

Source

Automated customer mining for banking products using machine learning models. The method involves collecting customer behavior data, screening it to extract transaction features, feeding the features into a trained neural network model, and marking customers as potential product targets based on the model's output. This allows accurate and efficient identification of customers likely to be interested in banking products, compared to manual selection.

Source

Automatically creating personalized electronic communications for individual customers using dynamic configuration of campaigns instead of manual segmentation. The system optimizes relevance and business outcomes for each customer by autonomously deciding products, offers, recommendations, etc. based on context like business needs and customer attributes. It provides personalized features like recommendations, content, offers, etc. for each customer through a single campaign configuration. The autonomous decision-making achieves "autopilot" for marketing strategies where electronic communications can effectively run on autopilot.

Source

Intelligent payment selection and routing using machine learning to optimize payment processing. The method involves receiving payment data, identifying payment information, retrieving client, account, and routing data, applying machine learning rules to predict the optimal payment route, and routing the payment using the predicted route. The machine learning determines the best route based on factors like payment amount, currency, history, etc.

Source

Method, device, system and media technology for improving bank customer retention rate by using sentiment analysis and machine learning to provide personalized services to bank customers. The method involves analyzing historical customer evaluation data using sentiment analysis to determine their emotional state. Then, combining the emotional state, transaction history, and behavioral data as input to a pre-trained big data model to generate recommended products and services for the customer. This targeted personalization enhances customer satisfaction and loyalty, reducing churn and improving retention.

Source

Dynamic return validation using generative adversarial networks (GANs) and reinforcement learning to optimize returns policies for individual customers. The system receives a return request, transaction history, and return rules. It applies a trained GAN using the customer data to determine return validity. Based on the GAN output, it recommends return actions like refusal or discounts. This allows personalized returns policies based on customer behavior to mitigate fraudulent returns.

Source

A machine learning system to predict personalized payment screens for invoices based on user transaction data. The system analyzes historical transaction features to understand user payment behaviors. It uses a machine learning model to predict probabilities of payment methods for each invoice. This allows generating customized payment screens with ordered payment methods tailored to each user, increasing payment rates and revenue for the financial service provider.

Source

Recommending banking products to customers based on their transaction history and correlation with other products. The method involves calculating correlations between a target customer's product transactions and other products. If the correlations are high, it indicates the target customer is similar to others who have those products. If the correlations are low, it indicates the target customer is dissimilar to others who have those products. By balancing high and low correlations, the method determines recommended products that are not already in the target customer's history but are correlated with products they do have.

Source

A system and method for optimizing bank architecture based on user data analysis. It involves using big data to analyze user information from a bank's data warehouse and then automatically adjusting the mobile banking app's features and functions for individual users to improve their experience. The app interacts with users, sends user data back to the warehouse, and provides services. A security module protects user identity and funds.

Source

System to provide customized financial solutions to bank customers based on analysis of their financial data, risk profile, relationship with the bank, and interest rates. It aggregates customer's financial portfolio to analyze risk vs profitability at an individual level. The analysis is presented to customers as dashboards and optimization suggestions to improve earnings/spends. This simplifies financial management, suggests steps to optimize portfolios, and leads to better banking experiences.

Source

Method to recommend financial services to individuals based on their transaction history and personal information. The method involves analyzing financial transaction data and user profiles to identify suitable financial products and services. It involves filtering and matching financial data related to the user with their portraits to recommend appropriate financial services. This reduces costs for financial institutions in promoting services and enables users to conveniently access tailored financial products.

Source

Automatically recommending bank products and services to clients based on their needs and determining if they acted on the recommendations using machine learning. The system engages clients to identify their needs, determines their current bank products, provides recommendations based on needs and current products, and uses machine learning to automatically determine if the client followed through with the recommendations.

Source

A method and device for pushing financial services to long-tail customers in a bank. The method involves screening long-tail customers based on basic information, using secure collaborative computing to analyze their behavior across multiple institutions, calculating accurate customer labels, and pushing tailored services based on those labels. It leverages data from multiple institutions like banks, internet companies, and government agencies to provide better insights into long-tail customers.

Source

Bank product recommendation method using a machine learning algorithm based on the honey badger algorithm to improve the accuracy and personalization of bank product recommendations for individual customers. The method involves generating an optimized customer group through screening from the original customer group and a reverse customer group. This improves diversity and quality to train a classification model based on the honey badger algorithm. The trained model is used to predict the recommended bank products for each customer based on their information.

Source

Identifying personalized retention strategies for banks to prevent customer churn and implementing those strategies. The method involves detecting when a customer is likely to leave the bank, then analyzing their interactions and transactions across channels to identify customized retention mechanisms. These mechanisms are then targeted to the customer to try and prevent them from leaving the bank.

Source

Personalized financial services experience for users based on their goals, values, and financial situation. The system allows users to select subjective financial goals and objective attributes like demographics. It converts these into numerical formats and compares them to averages for similar users. The results are presented back to the user in a personalized interface that segments into positive and negative areas based on whether the user is ahead or behind. This allows users to see how they compare to like groups and areas where they need improvement.

Source

Accurately recommending banking products to customers by considering transaction risk profiles instead of just similar customers' products. The method involves calculating risk entropy for each customer's transaction data in various risk dimensions. Customers with similar risk profiles are identified. If a target customer's risk entropy exceeds a threshold, their riskier products are recommended. If below threshold, the union of products from similar customers is recommended.

Source

Predictive modeling for targeted incentives in payment networks using neural networks. The method involves learning transaction patterns, generating probability density functions, and making predictions about future transactions. It changes account states based on the predictions and sends targeted notifications to account owners. This allows preemptive, personalized incentives to be offered to account holders for upcoming transactions at relevant merchants based on their historical behavior.

Source

User interface for making personalized payment recommendations at the point of sale to maximize benefits. The interface uses machine learning to analyze past transactions and rewards to determine the optimal payment method for each sale. It generates a recommended payment method and virtual number to display at checkout. The recommendations consider factors like reward points, cashback, miles, charitable donations, and interest rates. The interface filters expired benefits and predicts recommendations for future sales using a machine learning model.

Source

Determining real-time personalized offers for users based on dynamic user attributes and data sets from similar users. The offers are dynamically determined in real-time based on constantly updated user attributes and user behavior. Machine learning algorithms analyze the user's dynamic attributes and similar user data to determine eligibility and likelihood of acceptance. This allows tailored offers that adapt to changing user circumstances.

Source

Customized financial consulting service that leverages artificial intelligence to analyze user asset data and provide specialized financial advice tailored to their needs. The system collects financial information from multiple institutions using AI to minimize input from users. It matches financial planners based on expertise and allows users to select areas of interest. The AI analyzes financial and non-financial tendencies to recommend customized products. Users can also set goals, view statements, and get consulting services. The AI calculates taxes, investments, and liabilities.

Source

Smart card that provides personalized recommendations and decision support based on real-time data and advanced analytics. The smart card receives activity data from a user's devices and sends it to a server for analysis. The server arranges the data in a cognitive structure, processes it to determine choices and probabilities, and sends the results back to the smart card. The smart card displays the personalized options to aid the user's current activity. The system uses machine learning techniques to analyze dynamic, imperfect, and incomplete data in real-time for adaptive decision making.

Source

A contextual engagement decision engine that dynamically determines optimal digital identity and funding options for a given user interaction based on variables like point of engagement, user device, authentication method, and available funding sources. The engine communicates with multiple identity and payment providers to validate user identity, collect funding options, and then maps the interaction to an optimized output. It uses statistical models and machine learning to further optimize the output. This centralized, integrated approach enhances purchasing experiences by intelligently matching identity, payment, and funding sources for each interaction.

Source

Bank customer relationship management using AI to accurately determine customer importance and optimize banking systems. The method involves extracting correlation features between customer funds and capital flows using neural networks. It converts customer fund data into feature vectors, extracts adjacency features from the fund graph, and combines them through graph neural networks. The features are passed through a classifier to get probability values for customer importance. This provides a more accurate and comprehensive evaluation of customer importance compared to just using fund flow data.

Source