发明名称 |
SYSTEM FOR SPEND ANALYSIS DATA TRANSFORMATION FOR LIFE EVENT INFERENCE TRACKING |
摘要 |
Embodiments of the invention are directed to a system, method, or computer program product for a distributive network system with specialized data feeds associated with the distributive network for identifying and predicting times of life events within a level of certainty. Utilizing machine learning techniques the likelihood of occurrence of a life event it identified based on a compilation of data points including customer total spend, the magnitude of item or merchant level transactions, and the frequency of item or merchant level transactions. Once a threshold of characteristics is reached, the system identifies with a degree of certainty that an event will occur and a time frame in which it will occur, termed an event horizon. One the event horizon is generated with sufficient evidence from the data points, future actions are positively-biased towards the occurrence of the event. |
申请公布号 |
US2016314528(A1) |
申请公布日期 |
2016.10.27 |
申请号 |
US201514695252 |
申请日期 |
2015.04.24 |
申请人 |
BANK OF AMERICA CORPORATION |
发明人 |
Abbott Robert L.;Neurohr Michael William |
分类号 |
G06Q40/00;G06N7/00;G06N99/00;G06Q30/02;H04L29/08 |
主分类号 |
G06Q40/00 |
代理机构 |
|
代理人 |
|
主权项 |
1. A system for life event inference tracking, the system comprising:
a memory device with non-transitory computer-readable program code stored thereon; a communication device; a communicable linkage to a distributive network of specific network data feeds; a processing device operatively coupled to the memory device and the communication device, wherein the processing device is configured to execute the computer-readable program code to:
develop spending profiles for one or more life events based on historic data, wherein developing spending profiles include identifying a frequency and magnitude relative to a time frame for product category and merchant category transactions that provide a predictor that the one or more life events will occur;identify customer transactions occurring within a time range that utilizes a financial institution product;retrieve, utilizing a distributive network and the specific network data feeds, item level transaction data for products of the transactions occurring within the time range;categorize the products of the transaction and a merchant associated with the transactions;calculate using a learning application based on the developed spending profiles a probability of one or more potential life events occurring at a future time based on the categorized products and merchants associated with the transactions;trigger, based on a probability value, a point of certainty that a horizon life event associated with the one or more potential life events will occur for the customer, wherein the horizon life event is a specific life event and a specific time range where the horizon life event will occur in the future;distribute throughout an entity via the distributive network to private nodes the horizon life event for the customer;direct positively biased actions to the customer based on the horizon life event; andterminate the positively biased actions upon expiration of the horizon life event time range. |
地址 |
Charlotte NC US |