Telecommunications
Case Studies
Newsfor Telecommunications
AT&T monitors its network constantly offering seamless service and plans maintenance and upgrades optimally using machine learning
AT&T is automating network monitoring, using machine learning to predict traffic demand based on historical data, day and time, and generate alerts. All the equipments are monitored to detect anomalies and plan optimal predictive maintenance schedule.
Linked use case: Optimise network traffic load balancing
AT&T pulls sales leads from multiple systems to automate data entry into legacy systems using Robotic Process Automation
Using RPA AT&T has been able to automate data entry. Data related to sales leads is extracted from various sources and is automatically filled into enterprise system freeing up hours worth of time for employees. They have also been able to improve customer service by reducing the time taken to offer certain services like ethernet from days to hou rs.
Linked use case: Improve administrative productivity with Robotic Process Automation
Bharti Airtel reduces time to hire from weeks to days and offer-drop rate from 80% to 26% through predictive hiring
Airtel had a staggering 80% offer drop rate (i.e only 20% of offers were accepted). They used Belong''s AI platform to identify candidates who are likely to match the company profile and implement a targeted approach. They also redesigned the hiring process such as changing job titles to appeal better to the right candidates.
Linked use case: Identify key characteristics of successful employees for recruitment and career development support
British Telecom improves network security by using machine learning to detect real-time cyber threats
BT has deployed Darktrace''s Enterprise Immune System to protect its network and large datasets. The system records daily patterns of network activity and creates a baseline model of the network. Any deviations or anomalies are classified as threat instantly and alerts are generated.
Linked use case: Manage cybersecurity threats and regulatory reporting
British Telecom saves an estimated £100M a year using the automated contract analysis platform RAVN
BT has been using RAVN contract analysis technology to analyse its commercial contract documents and extract key provisions from them, with estimated savings of £100m a year.
Linked use case: Support review and design of supplier contracts
Equinix predicts customer churn with 90% accuracy using a machine learning neural network model
Equinix''s data science team have created a model which analyses different data for customer characteristics and provides the sales team with customers'' risk for churn with a 90% accuracy, along with possible reasons which can then be acted on.
Linked use case: Predict and drive customer retention and churn management
France Telecom''s Telekomunikacja Polksa realised that certain customers have a greater or lesser influences on networks of mobile phones users. If highly connected networkers churn then this is likely to cause a large ripple effect. To improve customer churn prediction and identification of who to retain they developed social graphs and analysis based on the transaction history and network connections of customers. This allowed them to improve prediction by 47%.
France Telecom Polksa improves customer churn prediction and identification of who to retain by 47% through analysis of customers and their social influence. The company realises
Linked use case: Predict and drive customer retention and churn management
Infinera will optimise its supply chain management to make better predictions about delivery dates using machine learning
Infinera will a predictive solution for its supply chain management. Based on machine learning, the technology analyses past variability in production lead times and logistics provider performance to offer real-time order promising and scheduling. The company aims to make better prediction of order delivery dates and optimise its supply chain as part of its recovering process of a net loss of $195 million in 2017. The pilot project will go live in the middle of 2018, starting with one manufacturing plant.
Linked use case: Optimise supply chain
MTN sped up their patent application rate with 50% fewer rejections using TurboPatent''s patent drafting automation platform
Maritime Telecommunications Network partnered with TurboPatent to begin patenting their inventions using their automation process, resulting in 20 new patents in under 14 months, 50% fewer patent office rejections and at a cost less than 40% of industry average.
Linked use case: Accelerate identification and protection of intellectual property
Neopost identifies customers at risk of churn with machine learning using PredicSis
Neopost has centralised all customer data and implemented PredicSis (a plug-n-play service available through Amazon Web Services) to generate lists of customers at risk of churn.
Linked use case: Predict and drive customer retention and churn management
Nokia aims to boost 5G network performance and cut costs with the use of machine learning
Nokia is considering three possibilities for machine learning and 5G in the race between suppliers to bring 5G service to their customers as quickly as possible. It aims at boosting network performance and cutting costs by applying machine learning to some of the problems that the complexity of the the new radio access networks pose.
Linked use case: Optimise network traffic load balancing
Orange Silicon Valley speeds up project completion using TARA machine learning hiring and project management platform
Orange Silicon Valley used TARA project management platform to match and hire a contractor and manage project scope, deliverables and deadlines, hiring and finishing quicker than other comparable projects.
Linked use case: Identify and source potential candidates in the market
Quickplay safeguards its data and interconnected systems with Darktrace’s AI-enabled cyber security product
Quickplay Media leverages Darktrace’s Enterprise Immune System in order to monitor its network activity and detect threats and cyber attacks in real time, while minimising falses positives. The company has been able to obtain total visibility of its network, get alerts on anomalies and abnormal behaviours that may be threats and act proactively to prevent and avoid harmful situations.
Linked use case: Automate cybersecurity systems
SK Telecom to prevent voice phishing cyber attacks using AI
SK Telecom in collaboration with South Korea''s finance watch dog, the Financial Supervisory Service (FSS), plan to combat voice phishing attacks with the use of AI. Based on the watchdog''s provision of financial fraud data, the company is building an AI system aimed at alerting callers if a voice phishing call is being suspected. The difference with older practices to identify such cases is that the system will base its predictions on the context of the calls rather than preset keywords. The company has stated that the system is expected to launch in the first half of 2019.
Linked use case: Manage cybersecurity threats and regulatory reporting
T-mobile reduces churn by up to 50% by identifying and retaining highly-influential ''tribe leader'' customers with advanced predictive modelling
T-mobile USA analysed the social relations between subscribers to understand its impact on churn. They identified ''tribe leaders'' who have strong influence in a large connected group. These leaders have outside impacts if they churn taking more of their network with them. Using this insight and the analysis T-Mobile was able to reduce churn by up to 50% by focusing on retaining these influencers.
Linked use case: Predict and drive customer retention and churn management
Telefonica O2 automates processing of more than 35% of outsourced business processes using robotic process automation
Telefonica O2 deployed Blue Prism''s RPA solution to automate outsourced back office operations. The aim was to reduce the cost of back office operations and cut its reliance on offshore recruitment to cope with spikes in workload. It also simplified changes to business processes.
Linked use case: Digitise and automate processes using Robotic Process Automation (RPA)
TigoUne reduces management system failure by 80% through a machine learning workforce management solution
TigoUne, a large Colombian telco, had six disconnected CRM systems that resulted in productivity issues for their 1,700 field engineers. Using ClickSoftware solutions the disparate systems were linked and AI was used to improve dispatcher and field engineering productivity. This resulted in more timely resource planning and scheduling.
Linked use case: Accelerate data integration from multiple sources
US cellular increases customer lifetime value by 61% by analysing website visitor behavior against online and offline sales, subscriptions and renewals using machine learning
US Cellular uses AI to quantify and improve the role of their website in driving in-store sales. They use Cardinalpath''s plaform to analyse website visitor behavior against online and offline sales, new service subscriptions, and service renewals using machine learning to map purchase intent. Using this data they were able to equate website actions to dollar value and optimise website.
Linked use case: Optimise website experience to improve engagement and conversion rates
Verizon monitors and optimises network performance in real-tim using machine learning to analyse network interface data
Verizon employs machine learning algorithms to monitor data from network interfaces such as routers and sensors measuring weather conditions and transactional data such as billing records. Using this data, trends are predicted to make adjustments to resource allocation as well as to detect anomalies within the network leading to much better performance.
Linked use case: Enhance product and service offering