Browse Prior Art Database

System for the computation of a Dynamic Resiliency Score (DRS) using Supervised Machine Learning

IP.com Disclosure Number: IPCOM000249430D
Publication Date: 2017-Feb-27
Document File: 5 page(s) / 90K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article describes a system and method for computing a Dynamic Resiliency Score (DRS), using Supervised Machine Learning techniques based on 7 factors of IT, Data, Application, Facilities, Process, People and Business Strategy. Additionally the DRS can also be computed using Neural Nets and Deep Learning.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 29% of the total text.

1

System for the computation of a Dynamic Resiliency Score (DRS) using Supervised Machine Learning

Disclosed is a system for computing a Dynamic Resiliency Score (DRS) using Supervised Machine Learning or Deep Learning techniques. The computation uses the 7 factors of IT, Data, Application, Facilities, Process, People and Business Strategy to compute this score. The DRS will be a value between 0 and 1, where a value close to 0 indicates poor Resiliency preparedness and a value closer to 1, indicates good Resiliency preparedness.

Introduction: In today’s enterprises, ensuring Business Continuity in the face of disasters (natural or man-made), is extremely critical. Businesses depend on multiple factors including Facilities, IT, Data, Applications, People, Process and Business Strategy. This idea outlines a system which will compute an instantaneous Dynamic Resiliency Score (DRS) between values 0 and 1.. This DRS score will use supervised machine learning to compute an instantaneous, a Dynamic Resiliency Score. This will be based on the values for the 7 key factors for the business and will use multi-variate regression to train a model. Since the past history of some of the factors like Business Strategy, Process or People cannot be obtained an average value will be used for training the model. Data for IT, backup, network logs etc will be available from the business and can be used for training the model. The DRS can be used to assess the business preparedness of a enterprise infrastructure.

The DRS system will continuously compute the Resiliency Score by taking inputs on IT infrastructure, Application, Data and other like Process, Business Strategy etc. This DRS score will be based on the trained regression model. A DRS score of ~ 1 would indicate very good business continuity preparedness and a DRS score of ~0 will indicate that preparedness is seriously lacking and needs to be immediately addressed.

An enhancement to the DRS system will be a system which is modeled using Neural Networks and based on Deep Learning. This model will continuously relearn will be able to predict more accurately

Description

Maintaining business continuity through resilience, is essential for businesses in today’s world of exponential growth of data, and the complexity of the systems. The advances in computing for example the Machine Learning, Statistical Learning, and Cognitive Computing provide useful insights from complex data. The difficulty in providing business resilience is that resilience has to be established through the interaction of business strategies, IT factors, natural factors some of which can be measured to great precision and some which cannot. The system proposed, tries to quantify all the factors for e.g. business strategy, process or people.

The system in this article, tries to estimate the 'Resiliency Score’ dynamically by quantifying all the factors for e.g. business strategy, process or people since you cannot ‘manage what you cannot measu...