Rohit Punnoose, Ph.D.

Abstract:

Many organizations undertake large-scale projects of application migration due to availability of scalable and cost-efficient technologies. Such legacy application migration projects are very complex since the process involves in-depth profiling of the applications.

During the initial profiling phase, it is imperative to understand the underlying complexities of individual applications, as well as the interdependencies among applications in the organization. This… Show more

Abstract:

Many organizations undertake large-scale projects of application migration due to availability of scalable and cost-efficient technologies. Such legacy application migration projects are very complex since the process involves in-depth profiling of the applications.

During the initial profiling phase, it is imperative to understand the underlying complexities of individual applications, as well as the interdependencies among applications in the organization. This analysis phase can take considerable time and effort, depending on number and complexity of the applications. The main goal of this paper is to provide a framework that provides a cost-effective and quick approach to study the interdependencies between legacy applications with minimal prior knowledge of application usage.

In this paper, we propose a framework that uses community detection algorithms and other established techniques from graph theory, to discover interdependencies of legacy applications within an organization, group these highly interdependent legacy applications in clusters, and finally sequence the clusters for migration to a modern platform. We study the proposed framework through three case studies, using network datasets from a large US organization.

The experimental results from the proposed framework suggests that legacy applications can be grouped into clusters with high interdependencies between each other. Also, the framework shows how organizations can then appropriately sequence the clusters of legacy applications into a phase-wise migration project, thereby reducing migration costs.

The proposed framework provides a valuable design input to organizations on how to determine the interdependencies between the various legacy applications that are in scope for migration to a modern platform. Such large-scale migration projects can be simplified and broken down to use a systematic approach, thereby reducing migration costs and data integrity challenges. Show less

Number of Citations: 160+
DOI: https://doi.org/10.14569/ijarai.2016.050904

Employee turnover has been identified as a key issue for organizations because of its adverse impact on work place productivity and long term growth strategies. To solve this problem, organizations use machine learning techniques to predict employee turnover. Accurate predictions enable organizations to take action for retention or succession planning of employees. However, the data for this modeling problem… Show more

Number of Citations: 160+
DOI: https://doi.org/10.14569/ijarai.2016.050904

Employee turnover has been identified as a key issue for organizations because of its adverse impact on work place productivity and long term growth strategies. To solve this problem, organizations use machine learning techniques to predict employee turnover. Accurate predictions enable organizations to take action for retention or succession planning of employees. However, the data for this modeling problem comes from HR Information Systems (HRIS); these are typically under-funded compared to the Information Systems of other domains in the organization which are directly related to its priorities. This leads to the prevalence of noise in the data that renders predictive models prone to over-fitting and hence inaccurate. This is the key challenge that is the focus of this paper, and one that has not been addressed historically. The novel contribution of this paper is to explore the application of Extreme Gradient Boosting (XGBoost) technique which is more robust because of its regularization formulation. Data from the HRIS of a global retailer is used to compare XGBoost against six historically used supervised classifiers and demonstrate its significantly higher accuracy for predicting employee turnover. Show less