By Shamil Assylbekov, PhD. & Devin Levy, Charter Communications
In the current paradigm of Operations acting in a reactive, post hoc manner, something has got to give. MSOs cannot continue to throw bodies at problems in efforts to remediate outages, customer impacting events and impairments. Instead, a data-driven Machine Learning (ML) approach needs to be utilized to change the tide for the better. Cable operators have the ability to merge heterogeneous data from various sources in efforts to qualify and classify problem areas. This will ultimately lead to ML-driven operations which will result in a better sustained customer experience and afford the opportunity for the MSO to work under a lean operations model while employing top engineers to do the work of what would have previously taken dozens of engineers to handle in a post-hoc world. Operational problems go past operations expenditure. Customer impacting events is the name of the game, and by utilizing different ML approaches for different issues, one can classify various events that occurred, provide actionable intelligence and network automation to curtail outages, reduce the mean time to resolution (MTTR) of events in the end providing a better customer experience. Initial efforts of our group have yielded a reduced MTTR for outages and impairments, less escaped defects for feature enhancements, actionable intelligence that affords us the opportunity to make data driven decisions rather than gut reactions or best efforts. This result was mainly achieved via the Deep Learning approach for the purposes of anomaly detection, and a mixture of ML approaches for the purposes of escaped software defect categorizations.
At Charter, ML has made Operations a more intelligent organization. Some of the decisions are now made with real time actionable intelligence via our own plethora of analytics; we now have ability to improve the customer experience on a daily basis. And, we encourage the adoption of this new operational transformation, for the betterment of our industry.