International Business Machines Corporation

Shuyan Lu

Eugene Irving Kelton

Yi-Hui Ma

John H Walczyk, Iii

Eliza Salkeld

Chuan Ran

Shanna Hayes

Yongchang Cui

Guandong Zhu

Junhui Wang

Willie Robert Patten, Jr

Brandon Harris

Weichen Wang

Yang Yang

Pu Yang

Russell Gregory Lambert

A system, platform, program product, and/or method for generating new composite insight templates that includes: running a machine learning model on a data set to obtain for each of a plurality of entities a risk score and feature-based insights; generating a list of top 'n' features input to the machine learning model that contributes to the risk score for each entity; grouping entities based upon similar features input to the machine learning model that contributes to the risk score for each entity; generating a decision tree for at least one of the group of entities; extracting, from the decision tree generated for the at least one of the group of entities, one or more feature-based insights; generating, by applying subject matter input, a new composite insight based upon the one or more feature-based insights; and adding the new composite insight to insight templates.

System and method to generate insight templates for risk probability analysis

Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises receiving transactional data from at least two users in a plurality of users; determining a pattern within the received transactional data based on a frequency-based domain conversion, wherein the pattern is associated with a determined periodicity; determining a delay within the received transactional data by identifying contextual factors associated with the received transactional data and measuring an amount of time between each identified contextual factors within a plurality of identified contextual factors using a signal processing algorithm; aligning the received transactional data from the at least two users by placing at least two signal forms associated based on the determined delay within the received transactional data at a same point; and generating a line graph depicting the aligned transactional data.

Vector alignment of signal lag

Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises determining a pattern within received data based on a periodicity associated with the received data; in response to a calculated signal score associated with the determined pattern of the received data meeting or exceeding a predetermined threshold transaction amount, tracing at least one location associated with the received data; and dynamically suspending an action associated with an account that generated the received data in response to the traced location not being associated with a historical baseline of the account.

Scaling transactions with signal analysis

Disclosed are techniques for quantifying physical qualities of a ball returned by a player using a loop drive technique, such as in table tennis, and generating a corresponding quantitative summary of the overall quality of the loop drive technique based on the quantified physical qualities. Image processing techniques are applied to historical video recordings of balls returned using loop drive techniques to quantify physical properties of said balls. A machine learning model is generated using the quantified physical properties to determine relative significance of specific qualities and their corresponding quantified values to the overall quality or success of loop drive techniques, such as in table tennis matches.

Capturing and quantifying loop drive ball metrics

Embodiments of the present invention provide a computer system a computer program product, and a method that comprises converting received data from a time-based domain to a frequency-based domain using a signal processing algorithm; identifying transactional noise within the converted data by identifying contextual factors based on a determined pattern, wherein the transactional noise is data associated with an identified fraudulent transaction; filtering the identified transactional noise by removing datapoints within the converted data that reaches a predetermined threshold of signal strength using the signal processing algorithm; and generating a line graph depicting removal of the data that is indicative of the identified transactional noise from the converted data.

Removal of transaction noise

Computer vision and deep learning techniques are leveraged to detect behavior patterns in transaction histories. A transaction timeline is built for a series of transactions, e.g., financial, and a graphic image is constructed representing the transaction timeline. The graphic image is then matched to a known behavior pattern using a cognitive system. The cognitive system is trained with historical timeline images having associated labels. In one example the graphic image is a bar chart and each financial transaction is represented as a bar in the bar chart having a height proportional to a transaction amount, the bar being located along a time axis of the bar chart according to the transaction date and being color coded according to the transaction type.

Classifying behavior through system-generated timelines and deep learning

A detection modeling system has a processing device and a memory coupled to the processing device. The detection modeling system is configured to obtain health value data associated with an analytical model, determine a time period at which the model was trained based on the obtained health value data, and identify a survival time period of the model based on the determined time period at which the model was trained and a failure time period of the model. The detection modeling system is further configured to repeat these steps to determine a survival time period for a plurality of analytical models, and perform a survival analysis based on the survival time period for the plurality of analytical models.

Systems and methods for alerting to model degradation based on survival analysis

A detection modeling system performs a distribution analysis to alert to model degradation. The detection modeling system may have a distribution analysis module configured to perform an alerting process in conjunction with a processing device. The distribution analysis module may select, by the processing device, model metrics for analysis, the model metrics being a measure of a parameter associated with the analytical model and determine normal distributions for model metric results for each of the selected model metrics. The detection modeling system may further receive model metric values for each of the selected model metric, compare, by the processing device, the model metric values to the normal distributions for model metric results for each of the received model metric value, and alert, by the processing device, to model degradation of the analytical model based on the comparison of the model metric values to the normal distributions for model metric results.

Systems and methods for alerting to model degradation based on distribution analysis

A method, system, and computer program product for computer vision modeling are provided. The method identifies a set of transactions. A set of categorical behavior transaction types are determined for the set of transactions. The set of categorical behavior transaction types are mapped to a set of colors in a color coordinate system. The method scales color component values of the set of colors in the color coordinate system to generate a pattern of colorized units at intervals along a timespan of the set of transactions. The method generates a fraud detection model based on the set of transactions and the color component values.

Encoding multi-dimensional information for deep vision learning

Disclosed are techniques for quantifying body postures of a player employing a loop drive technique to strike a ball, such as performed in table tennis activities. A video recording of a player striking a ball with a loop drive technique is received and divided, using image processing techniques, into two segments: the first concerning player body postures before the ball is hit, and the second concerning body postures from the moment of impact between the ball and racket and the subsequent follow-through body postures. Then, image processing techniques are again leveraged to isolate and quantify specific body postures contributing to a loop drive technique in a given segment.

Capturing and quantifying body postures

Disclosed are techniques for leveraging machine learning to generate posture adjustment values for specific body postures of a player to improve loop drive techniques, such as in table tennis. Video clips of a player hitting a ball with a loop drive technique are analyzed to determine values for specific body postures and qualities of the ball after being hit. A machine learning model is generated to analyze relationships between body posture values and ball qualities. Upon receiving a video clip of a live session of a player hitting a ball using a loop drive technique, the machine learning model is used to generate adjustment values for body postures of the player to impart improved loop drive qualities to the ball, such as faster topspin.

Growing community of inventors

Cary, NC, United States of America

Shuyan Lu