Case studies on using natural language processing techniques in customer relationship management software
- PDF / 1,639,232 Bytes
- 21 Pages / 439.642 x 666.49 pts Page_size
- 52 Downloads / 166 Views
Case studies on using natural language processing techniques in customer relationship management software ¨ u¨ Ozan1 S¸ukr Received: 1 April 2020 / Revised: 27 August 2020 / Accepted: 27 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract How can we use a text corpus stored in a customer relationship management (CRM) database for data mining and segmentation? To answer this question, we inherited the state of the art methods commonly used in natural language processing (NLP) literature, such as word embeddings, and deep learning literature, such as recurrent neural networks (RNN). We used the text notes from a CRM system taken by customer representatives of an internet ads consultancy agency between 2009 and 2020. We trained word embeddings by using the corresponding text corpus and showed that these word embeddings could be used directly for data mining and used in RNN architectures, which are deep learning frameworks built with long short-term memory (LSTM) units, for more comprehensive segmentation objectives. The obtained results prove that we can use structured text data populated in a CRM to mine valuable information. Hence, any CRM can be equipped with useful NLP features once we correctly built the problem definitions and conveniently implement the solution methods. Keywords Customer relationship management · Word embeddings · Machine learning · Natural language processing · Recurrent neural networks
1 Introduction CRM is a sine qua non of the sales and marketing operations of most businesses. A good CRM software not only manages relationships with the customers but also manages every related data. Since recent advances in technology make it possible to store a massive amount of data, data mining in CRM has gained significant popularity in associated fields. In this study, we concentrate on the structured text data populated in the CRM of a Turkish internet advertising consultancy agency called AdresGezgini Inc. (from now on referred to as “the company”). The company extensively uses telephony since it is essential S¸u¨ kr¨u Ozan
[email protected] 1
AdresGezgini Inc. Research & Development Center, ˙Izmir, Turkey
Journal of Intelligent Information Systems
not only for marketing processes but also for customer relationship management. Moreover, it is well-known that if the services or products already meet customer needs, telephone calls guarantee customer satisfaction and loyalty (Feinberg et al. 2000). Especially companies that prefer telephony as the significant sales and marketing strategy expect the customer representatives (a.k.a. the agents) to take notes regarding customer calls. These notes reflect the agents’ idea about the corresponding call, which, moreover, reflects the customers’ general attitude and ideas about the company and its services. Agents try to explain the conversation they performed in their own words briefly. It is worthy to emphasize that customers’ sensitive information, such as contact information, financial information, i
Data Loading...
