TalkTalk is the UK’s leading value for money consumer and B2B telecoms provider. Their mission is to deliver affordable, reliable, simple, and fair services for everyone.
In 2016, TalkTalk engaged endjin to investigate a very specific problem: "we're seeing unexplained spikes in our network telemetry data". Every day over 1 million set top box devices generate 10 GB of diagnostic data, and although the network operations team could spot unusual patterns, data analysis was a labourious, manual process that often exceeded the SLAs to resolve such issues. Endjin ran a series of data science experiments to establish if an anomaly detection model could identify known anomalies in historic data.
These experiments indicated that the raw telemetry needed to be processed in order to improve the signal to noise ratio, after which, the anomaly detection algorithm could be applied effectively to each stream of related events to identify anomalous activity. The results could be aggregated, denormalized, and correlated to show relationships between different anomalous events and higher level patterns across periods of unusual activity.
Cortana Intelligence Suite was used to productionise the end-to-end solution - orchestrating the data movement and transformation with Azure Data Factory, hosting and running the model in Azure Machine Learning, and displaying a series of interactive and dynamic exploratory dashboards in Power BI that gave the team on-demand access to the latest data. With the Anomaly Detection Platform in place, the customer insight team could understand unexplained issues and outages, identify patterns of unusual behaviour, carry out proactive support and maintenance, improve customer experience, and reduce customer churn by making customer quality investments based on reliable data insights.
In 2017, building upon the Anomaly Detection Platform, endjin were asked to create a Modern Data Platform to store and analyze vast amounts of hitherto untapped customer telemetry to enable TalkTalk to gain deeper insights about customer behaviour, quality of service, customer experience and churn prediction, while designing for data security and GDPR considerations.
— Ilario Corna, TalkTalk
Dentsu Aegis Network is a global media group that specializes in Media, Digital and creative Communications services that Innovate the way brands are built.
They sought endjin's help in designing and building a modern data processing pipeline to enable Reporting as a Service for their clients' digital campaigns.
Through a production quality, proof-of-concept architectural blueprint, based on current best practices around Azure cloud architecture - orchestration with Azure Data Factory, DevOps tooling and processes with Azure DevOps, and operational monitoring with Application Insights - endjin demonstrated how to run flexible, extensible, and scalable processing pipelines in the cloud.
With extensibility points around multi-tenancy for onboarding new customers and integrating new processing requirements, and fully embedded Power BI custom reports for external sharing and consumption, Dentsu Aegis Network had a best of breed Reporting as a Service solution, backed by a future-proof Modern Data Pipeline.
— Lana Lall, Director, Project Management Office, Dentsu Aegis Network
Vubiquity connects content owners and video providers to deliver entertainment to viewers on any screen. Working with nearly 650 leading film studios, television networks, and independent producers, Vubiquity is one of the world's leading providers of premium content to top OTT platforms.
Established in 2006, Benchpeg is the most widely read online jewellery magazine in the UK. The Benchpeg weekly newsletter reaches 10,000 readers in the Jewellery & Watch industries both nationally and internationally.
Benchpeg.com was replatformed onto Vellum – endjin's Azure-based Content Management Platform – which has been engineered to provide modern web best practices (responsive design, SEO, structured data, optimized page size & speed, accessibility, open graph for social media) out of the box.
Since re-launch, page views increased by 25%, session duration increased by 40%, Adsense revenue increased by 232%, and page RPM increased by 169%. More importantly, the effort required to produce weekly content has decreased from 4 days to 2 days, allowing more time to be spent on business development.
— Rebecca van Rooijen, Founder, Benchpeg
Risk management strategies require multiple layers of protection that limit the pathways that could result in a data loss or breach.
Endjin have worked with some of the largest companies in the world to create a security model and data privacy architecture for the Microsoft Cloud, which we subject to external audit by both clients and independent security consultants.
Leveraging Microsoft's impressive array of Azure certifications, and using technologies such as Key Vault and SQL Server Always Encrypted, we help you to employ the latest data encryption, replication and monitoring, ensure rigid access controls, auditing and application configuration within the organization.
Businesses depend on getting data to and from the cloud securely & reliably: enriching, transforming and manipulating it. Endjin's Modern Data Platform Blueprint is a culmination of the IP, process, and knowledge we have accrued over many years developing enterprise-class data solutions in the cloud, packaged up to help you achieve your data vision.
Built on top of endjin's Modern Data Platform, endjin's Anomaly Detection Platform can be used to identify, classify, and visualize anomalies in device telemetry or customer behaviour, and automatically feed back into your support procedures.