TY - GEN
T1 - Telecommunications Customer Service Improvement Through Big Data Analytics
AU - Shongwe, Thabile
AU - Malatji, Masike
AU - Pretorius, Jan Harm Christiaan
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Some telecommunications companies have already initiated big data analytics projects to extract value-adding insights from the data, but the tools in place are not always optimally utilised. One of the challenges facing telecommunications companies in this regard is the difficulty in choosing the right software and hardware tools appropriate for their environments. This paper investigated the big data analytics tools and applications utilised within the telecommunications industry of South Africa (SA) to improve customer services. A non-probability purposive sampling technique to recruit about thirty-five data scientists, analysts, managers, and engineers was followed. The following tools were found to be widely utilised: Statistical Analysis System, Hadoop, Google Cloud Platform, Google BigQuery, Amazon Web Services, PySpark, Splunk, PostgreSQL, Oracle, Pandas DataFrame, and Cloudera. The tools were found to be utilised at varying degrees of technology adoption and comprehensiveness depending on factors such as business requirements, affordability, and available skillset within the business. It was further found that many of the telecommunications companies in SA use big data analytics to improve customer experience and loyalty, reduce customer churn, optimise partnership networks, increase automation, improve fraud detection, have a single view of customers, and engage in operational intelligence and Internet of Things data. The limitation of the study was that respondents were recruited only from LinkedIn and thus excluding those who are not necessarily on social media platforms. Nonetheless, the respondents came from three of the 'big four' South African telecommunications companies. Future research could explore the study with a more diverse and higher number of respondents, employ personal and focus groups for in-depth analysis, or carry out a survey on the type and level of big data analytics skills.
AB - Some telecommunications companies have already initiated big data analytics projects to extract value-adding insights from the data, but the tools in place are not always optimally utilised. One of the challenges facing telecommunications companies in this regard is the difficulty in choosing the right software and hardware tools appropriate for their environments. This paper investigated the big data analytics tools and applications utilised within the telecommunications industry of South Africa (SA) to improve customer services. A non-probability purposive sampling technique to recruit about thirty-five data scientists, analysts, managers, and engineers was followed. The following tools were found to be widely utilised: Statistical Analysis System, Hadoop, Google Cloud Platform, Google BigQuery, Amazon Web Services, PySpark, Splunk, PostgreSQL, Oracle, Pandas DataFrame, and Cloudera. The tools were found to be utilised at varying degrees of technology adoption and comprehensiveness depending on factors such as business requirements, affordability, and available skillset within the business. It was further found that many of the telecommunications companies in SA use big data analytics to improve customer experience and loyalty, reduce customer churn, optimise partnership networks, increase automation, improve fraud detection, have a single view of customers, and engage in operational intelligence and Internet of Things data. The limitation of the study was that respondents were recruited only from LinkedIn and thus excluding those who are not necessarily on social media platforms. Nonetheless, the respondents came from three of the 'big four' South African telecommunications companies. Future research could explore the study with a more diverse and higher number of respondents, employ personal and focus groups for in-depth analysis, or carry out a survey on the type and level of big data analytics skills.
KW - analytics
KW - big data
KW - business intelligence
KW - telecommunications
UR - http://www.scopus.com/inward/record.url?scp=85148699219&partnerID=8YFLogxK
U2 - 10.1109/ICE/ITMC-IAMOT55089.2022.10033176
DO - 10.1109/ICE/ITMC-IAMOT55089.2022.10033176
M3 - Conference contribution
AN - SCOPUS:85148699219
T3 - 2022 IEEE 28th International Conference on Engineering, Technology and Innovation, ICE/ITMC 2022 and 31st International Association for Management of Technology, IAMOT 2022 Joint Conference - Proceedings
BT - 2022 IEEE 28th International Conference on Engineering, Technology and Innovation, ICE/ITMC 2022 and 31st International Association for Management of Technology, IAMOT 2022 Joint Conference - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 28th IEEE International Conference on Engineering, Technology and Innovation, ICE/ITMC 2022 and 31st International Association for Management of Technology, IAMOT 2022 Joint Conference
Y2 - 19 June 2022 through 23 June 2022
ER -