Sriram Rajagopal

Challenges and experiences in deploying enterprise crowdsourcing service

The value of crowdsourcing, arising from an instant access to a scalable expert network on-line, has been demonstrated by many success stories, such as GoldCorp, Netflix, and TopCoder. For enterprises, crowdsourcing promises significant cost-savings, quicker task completion times, and formation of expert communities (both within and outside the enterprise). Many aspects of the vision of enterprise crowdsourcing are under vigorous refinement. The reasons for this lack of progress, beyond the isolated and purpose-specific crowdsourcing efforts, are manifold. In this paper, we present our experience in deploying an enterprise crowdsourcing service in the IT Inventory Management domain. We focus on the technical and sociological challenges of creating enterprise crowdsourcing service that are generalpurpose, and that extend beyond mere specific-purpose, run-once prototypes. Such systems are deployed to the extent that they become an integrated part of business processes. Only when such degree of integration is achieved, the enteprises can fully adopt crowdsourcing and reap its benefits. We discuss the challenges in creating and deploying the enterprise crowdsourcing platform, and articulate current technical, governance and sociological issues towards defining a research agenda.

Accelerating the Deployment of Security Service Infrastructure with Collective Intelligence and Analytics

With the increasing complexity of IT outsourcing environments thousands of servers and their configurations are increasingly managed by globally distributed teams. This requires a flexible identity access management process in place to efficiently provision necessary access rights for a given system, only if users need it, when they need it and for only as long as they need it. In this paper we present a novel approach to discovering required role permissions by integrating system data and enterprise crowd sourcing (a process where a group of experts solve problems through collaboration). By mining server registries, compliance repositories (such as user revalidation records), we derive a set of servers and the respective access rights for each team member. This data is then validated and updated by one or more team members using the principles of crowd sourcing. We show that this approach improves the role discovery process and accelerates the deployment of the security service infrastructure.

API Terms and Conditions as a Service

Service Oriented Architecture (SOA) has evolved from business-to-business interactions, into the new API model that enables open partnerships and interoperability with just about anyone. In SOA, terms of service (ToS) and service level agreements (SLAs) were agreed upon on one-to-one basis, as the Web service interfaces were defined. In contrast, API ecosystems appeal for self-serve and instant gratification, being able to access, try and buy an API with a single click. As business teams and citizen developers access API ecosystems, they will want to quickly identify APIs that conform to their legal and usage terms requirements. For example, a large, established enterprise would not be as keen to give up their brand permission easily through use of a 3rd party API, whereas a citizen developer would probably not be concerned too much. Therefore we see a need to be able to automatically assess API terms of service to facilitate comparison and selection of multiple APIs from different providers. To enable API consumers to navigate this flood of APIs, we present a system that simplifies API terms of service creation and assessment. The core of the proposed system is a common API terms of service data model, which captures legal and entitlement capabilities. The system enables profile-based search, thereby allowing users to specify their terms of service requirements relevant to different roles that they may have in the ecosystem (e.g. citizen developer, enterprise procurement officer, etc.).

Crowd-Enabled Technical Writing Services

Availability of high quality technical documentation is a critical enabler for users to fully take advantage of service capabilities, such as Cloud-based offerings where clients interact with the service via a portal and have no direct access to a service support. Technical writers are relying on the input from subject matter experts (SMEs) to create usable portal content. This disrupts service operation and reduces the productivity of the entire service offering team. While technical documentation may include contributions from a large distributed team, it often results in disconnected content with different writing styles. In this paper, we describe Scribe Crowd, a service for managing the process of composition of technical documents. Based on the principles of crowdsourcing, where a task may be outsources to many qualified agents, Scribe Crowd manages the distributed process of documentation and assigns incomplete pieces of write-up to appropriate experts. We present how Scribe Crowd has been used to engage over 120 business consultants to efficiently create content for 450 documents as part of an enterprise learning portal that serves information about banking, insurance and financial markets.

Model for Service License in API Ecosystems

Rapid growth and consumption of REST APIs is generating new types of service marketplaces, which are dynamic and complex networks of providers and consumers. Existing models for software licenses and service standards, such as WDSL fall short of providing flexible frameworks for capturing the requirements that this newly created environment demands. Gaps exist in support for multi-pricing agreements across multiple providers and consumers, support for both usage and capacity events and automated generation and composition of licenses. Developers are accustomed to self-serve model, where they create and deploy new applications on the Cloud with a few mouse clicks, employing one or more available APIs. As a result, there is a need to be able to automatically assess existing licenses, compose new ones and understand their dependencies in order to shorten the time-to-value for new services. In this paper, we propose a model-driven approach for defining API service licenses, which provides capabilities to capture business and legal constraints, enable license metric calculation, QoS calculation and service pricing rules. We present API SLA analyzer system, which utilizes proposed license model to uncover SLA violations in real-time.

Server Hunt: Using Enterprise Social Networks for Knowledge Discovery in IT Inventory Management

Locating IT Inventory Management information is a challenging task, as the knowledge gets transferred among employees that move within or leave the context of a large organization. Information that relates to IT inventory is hidden in the knowledge of individual team members. This fact is not reflected in organizational expertise repositories and therefore locating those employees becomes a cumbersome manual process, if not intractable. We present an expert discovery service that leverages the professional social network of an employee, who was the last known person to hold the desired inventory information (such as application and server configuration settings, passwords, etc.) but is no longer available. Evaluation results suggest that this method reconstructs the desired information more than 80% of the time, as per our experiment involving 50 cases. We demonstrate how a carefully designed crowdsourcing approach can effectively extract the desired information from the employees professional social network and discuss its limitations.

Workload configuration and client strategy discovery using crowdsourcing

Using enterprise crowdsourcing service we have engaged multiple teams that interact with 300 clients to obtain insights into workload configurations on client infrastructure, identifying over 400 new project/revenue opportunities.