Digital technologies have led to the application of new-age technologies that operate with minimal human intervention. And while they may heighten productivity and drive growth, any failure can pose a significant challenge for IT and DevOps teams to resolve. An incident or service disruption is an IT manager's worst nightmare. Very often, factors such as cybersecurity breaches, human error, and the accelerated pace of innovation place significant pressure on enterprises' IT infrastructure, leading to system failures and outages impacting the bottom line. According to the ITIC 2021 Hourly Cost of Downtime Survey, 44% of participants (of 1,200 global organizations) said that hourly downtime costs anywhere from $1 million to over $5 million.

Reducing the number of failures in a production system is one of the most challenging problems in technology driven industries, such as, the online retail industry. To address this challenge, change management has emerged as a promising sub-field in operations that manages and reviews the changes to be deployed in production in a systematic manner. However, it is practically impossible to manually review a large number of changes on a daily basis and assess the risk associated with them. This warrants the development of an automated system to assess the risk associated with a large number of changes. There are a few commercial solutions available to address this problem but those solutions lack the ability to incorporate domain knowledge and continuous feedback from domain experts into the risk assessment process. As part of this work, we aim to bridge the gap between model-driven risk assessment of change requests and the assessment of domain experts by building a continuous feedback loop into the risk assessment process. Here we present our work to build an end-to-end machine learning system along with the discussion of some of practical challenges we faced related to extreme skewness in class distribution, concept drift, estimation of the uncertainty associated with the model's prediction and the overall scalability of the system.

Thousands of incarcerated people in Arizona have been kept behind bars by a software glitch, according to a report by KJZZ broadcast Monday. Anonymous whistleblowers from the Arizona Department of Corrections whistleblowers leaked details about the situation to the Phoenix NPR member station. Arizona has the fifth highest imprisonment rate in the country, and its incarcerated people are mostly nonviolent drug offenders. In 2019, the state Legislature passed a law aiming to change that by providing a way for nonviolent criminals to secure early release. For every seven days spent in a GED or substance abuse treatment program, an incarcerated person can shave three days off a sentence.

Change management as we know it is outdated and ineffective, with nearly 70 percent of all change projects failing to achieve their goals. That's why today's IT teams are no longer just solving change management issues – they're predicting them. The most common IT service management (ITSM) issue during a large change is an application outage, when a system or platform shuts down and is no longer operational. Something as simple as email migration can wreak havoc on IT teams and stakeholders without proper change management protocol. When large technology changes like email migrations are not properly planned, servers can overload and ill-equipped service desks are unable to handle the influx of requests.