Spend leakage in a cloud estate manifests in many forms and requires a careful analysis of various metrics. We present a suite of features to detect such behavior and provide recommendations for optimization. We apply the proposed solution in practice by presenting a real-world case-study. Through this case-study we demonstrate how many cases of spend leakage go unnoticed by simple handles to manage cloud estate, and how the solutions proposed in the paper can enable the business with better foresight and control on the cloud costs.

Event correlation provides a powerful lever to analyze the events data to better manage the enterprise IT systems. While many event correlation algorithms are present in literature, applying them in practice presents many real-world challenges. In this paper, we present our experience with the challenges, the workarounds, and the opportunities in using event correlations in enterprise IT systems. We propose a domain-aware way to select the right scope of events for correlation, with self-tuning parameters and recommending right correlation signatures based on the use-case. We present the effectiveness of our ideas with a real-world case-study.

Organizations across the globe require a reliable anomaly detection solution that allows for continuous quality control. Considering the scale and complexity of infrastructure, the most common methods include setting a blanket threshold by using knowledge of the experts or by applying simple statistical measures, which results in an alarm deluge. In this paper, we propose an approach to derive optimal thresholds by analyzing both the temporal and spatial properties of metrics related to entities. Additionally, our solution also self-tunes and self-learns to accommodate the tacit knowledge of experts and domains constraints. We demonstrate the effectiveness of our solution through a series of experiments and a real-world case study.

Spend leakage in the procure-to-pay process is one of the prominent challenges that organizations across the globe face. Given the complex dynamics of the procurement process, spend analysis heavily relies on the tacit knowledge of experts. In this paper, we address the problem of detecting maverick spends using a data driven approach. We present approaches to model the behavior dynamics of the procurement process, detect mavericks, and recommend alternate procurement options. We demonstrate the effectiveness of this solution through a real-world case-study.

Today's enterprises heavily rely on their batch systems to ensure smooth business operation. Any delay in these processes has direct impact on sales, revenue, customer experience, and brand image. In this paper, we present an approach to predict these batch processes and generate ahead-of-time notifications of potential batch-induced outages. We present several case-studies to demonstrate the effectiveness of the proposed solution in various real-world scenarios.

Today's IT systems heavily rely on IT support for smoother and faster operations. Any application or infrastructure issue is reported by tools or end-users in the form of a trouble ticket. The information about actual issue is hidden inside these ticket descriptions and is provided in different ways. In this paper, we address the problem of extracting the issues from these ticket descriptions. We break the problem into different sub-problems each presenting different challenges and hence requiring different solutions! We present our experience of applying theory into practice by presenting a real-world case-study.

The complexity and continuous evolution of enterprise systems is making it increasingly difficult to maintain the predictability of the system. The system managers are often unaware of the impact of an action across various layers of enterprise IT ranging from business functions, to applications, to IT infrastructure. Due to lack of this transparency, many risks go unnoticed leading to business outages or violations of Service Level Agreements (SLAs). In this paper, we address this problem of impact analysis of an action of an IT component on the enterprise system. We present novel techniques to model various aspects of system dependencies and then present algorithms to perform impact analysis. The ideas presented in this paper have been developed by applying them in real-world environments.

In this paper, we address the problem of transition of IT operations from one service provider to another. We present analytics-driven solutions to generate a transition plan while addressing various aspects such as coverage, risk, time, and cost. We model the IT operations through graphs and use the well defined problems in graph theory to build solutions for transition planner. We demonstrate the proof-of-concept of proposed ideas using a real-world case-study.