Browse Prior Art Database

Technique for maximizing the capacity utilization of marketing channels while optimizing marketing campaigns to improve ROI over limited-capacity marketing channels by applying the concept of rolling forward unused capacity in the marketing domain.

IP.com Disclosure Number: IPCOM000235829D
Publication Date: 2014-Mar-26
Document File: 4 page(s) / 55K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article describes a technique for maximizing the capacity utilization of marketing channels during optimization of marketing campaigns through the technique of rolling forward unused capacity.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 39% of the total text.

Page 01 of 4

Technique for maximizing the capacity utilization of marketing channels while optimizing marketing campaigns to improve ROI over limited -capacity marketing channels by applying the concept of rolling forward unused capacity in the marketing domain.

Disclosed is a procedure to address the unused channel capacity problem while optimizing marketing campaigns over limited capacity marketing channels in the Enterprise Marketing Management (EMM) domain. It improves on Prior art US8285583, US20090177522, US20120185326. Using the techniques in this prior art, several (competing) marketing campaigns can be simultaneously optimized across channels. To be able to effectively process the large volume of data (millions of proposed customer contacts) generated by the input marketing campaigns, the current algorithm divides the contacts (customers) into small sized chunk containing a few thousand customers each. Each customer chunk is allocated a

proportionate amount of marketing channel capacity so that the problem is turned into several sub problems of optimizing capacity over a few thousand contacts. This problem will not arise if all proposed customer transactions can be processed simultaneously in a reasonable time frame. However, even modern-day computers do not have enough resources like memory and CPU to be able to process multiple millions of records of data simultaneously so creating customer chunks is necessary

As a side-effect of dividing the problem into customer chunks, it has been observed that in many cases one or more chunks might not be able to utilize the capacity allocated to that chunk, The reason is that the transactions in that chunk fail to satisfy one or more business rules or constraints or are found to be sub-optimal compared to other transactions. As a result we fail to consume the maximum permissible channel capacity and the channel remains under-utilized. An under-utilized channel capacity means a direct loss to marketing business.

Suppose that we are running several marketing campaigns which generate leads (proposed contacts) for 1 million customers. Among these contacts, there are 10,000 customers eligible to receive a particular product offer on the Phone Channel (Direct Marketing using a Call Center) every day. If the Call Center (Phone Channel) has a capacity of 1000 phone calls a day, marketers will need to select 1000 most-profitable customers to maximize the return on the investment into the Phone Channel. To solve this problem, the current optimization algorithm will create 10 chunks containing 100000 customers each. Each chunk will get an equal share of the Phone Channel's capacity: it can select 100 calls (offers) on the Phone Channel.

The problem in this approach is, suppose a given chunk has fewer than 100 proposed contacts over the Phone Channel that satisfy the marketing rules / constraints, it will fail to give 100 offers. This will result in wasted Phone Channel capacity. At the same time, there m...