Browse Prior Art Database

Method and System for Predicting Potential Customers using Online Behaviour and Offline (Backend) Platform Information

IP.com Disclosure Number: IPCOM000247832D
Publication Date: 2016-Oct-06
Document File: 3 page(s) / 55K

Publishing Venue

The IP.com Prior Art Database

Abstract

A method and system is disclosed for predicting potential customers using online behaviour and offline (backend) platform information.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 33% of the total text.

Page 01 of 3

Method and System for Predicting Potential Customers using Online Behaviour and Offline (Backend) Platform Information

Traditionally, sales teams rely on automated marketing systems to generate potential sales leads based on marketing programs such as webinars, emails, and paid advertisements. When providing anything as a service (XaaS) such as SaaS or PaaS solutions, it becomes more and more important to collect customer information during trial registration process at a backend platform as well. It is usually difficult to prioritize sales leads nurturing activities when there are hundreds registrants every day, especially when there are only limited digital sales representatives. Therefore, a solution is required that targets to solve a XaaS specific sales leads prediction problem, which doesn't only use the user online behavior information, but also use the offline backend platform information. The solution needs to provide a data science based methods and a proved cognitive system to predict high potential XaaS customers, so that it enables sales team to prioritize and nurture the sales leads.

Disclosed is a method and system for predicting potential customers using online behaviour and offline (backend) platform information. The method and system predicts high potential XaaS customers by monitoring online behaviour information and offline backend platform information of the customers. The information is then scored using a new XaaS CES scoring technique.

In accordance with the method and system, the user behaviour that is collected online can be such as, but not limited to, marketing events, webinar, page views, clicks, duration of visits, referral, and live chat. User metrics are ranked, weights are assigned for each metrics and are used to multiply each index. Ci is ranked as the highest KPI, then it has weight of w/n (7/7 in this case). Click Depth Index: (session # > avg page views #)/total session #. The number of sessions having more than "n" page views is divided by the total number of sessions by the user. This index calculates the percentage of sessions a visitor clicks deeply into the website. The depth, depends on "n." For every session that a visitor's page views exceed "n," the engagement score increases. Ri: Recency Index: (session # > avg page views # in the past avg active weeks)/total session #. The number of sessions having more than "n" page views that occurred in the past "n" weeks divided by the total number of sessions by the user. The recency index calculates the percentage of sessions that a visitor returns to the website in a set amount of time (n) and views enough pages (n) to be considered engaged. Every time a visitor completes both actions, the engagement scores increases. Di: Duration Index: (session # > avg duration time)/total session #. The number of sessions longer than "n" minutes is divided by the total number of sessions by the user. The duration index calculates the percentage of a visit...