Browse Prior Art Database

System and Method for Lifetime Liability Assessment and Prediction

IP.com Disclosure Number: IPCOM000246432D
Publication Date: 2016-Jun-06
Document File: 4 page(s) / 248K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is an automated device to assess and predict individual financial liability or financial risk at year N from today. The device and application uses predictive and non-linear regression models and the Stochastic Optimization model, as well as other devices to formulate financial predictions.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 57% of the total text.

Page 01 of 4

System and Method for Lifetime Liability Assessment and Prediction

The novel contribution is an automated deviceto assess and predict individual financial liability or financial risk at year N from today using the following:

1. Predictive model to estimate the probability of occurrence of a life event in the Xth year from today and the entire life correlated event paths using a higher order state-action Markov transition model. Life events include but are not limited to employment, marriage, home ownership, vehicle ownership, job promotion, job loss, education, skills training, illness, etc.

2. Non-linear regression model to predict Markov state transition rates using person's environmental, developmental, and demographic variables and the associated predicted evolution

3. Scenario generation and scenario aggregation model to create different paths for various event sequences and their associated timing

4. Model to predict cash intake or outflow sequence associated with each predicted life event and the timing of that event

5. Stochastic Optimization model to tune the transition rate parameters within admissible range to minimize the liability/risk

6. Re-computation of timing of other correlated events due to user initiated changes in the timing of certain events using impact propagation model

Figure 1: Lifetime Event Playbook

Figure 2: Behind the Scene: Analytics Process Flow Model

1


Page 02 of 4

The state transition delays are Erlang-distributed random variab...