click here to download the abstract project
ABSTARCT
In many organizations, machine learning techniques are used for analyzing large amount of available data and information for decision making process. In educational sector, Machine learning is used for wide variety of applications such as suggestion to the students based on 10th mark and interest. One of the
most important milestones in an individual’s life involves self-analysis, critical thinking and finally decision making. This paper represent survey results on which academic decisions they concern and the variables involved in them. Using machine learning algorithms, it predicted courses/institutions in a real case study to support decision making. The choice of the career is influenced by views of your parents, friends, relatives, teachers and the media. Today with a wider choice and an ever increasing competition, you need to plan your career wisely and at the earliest. While choosing a stream after 10th, a training course or a career and 12th groups you should know your abilities, interests, and personality. Besides these you should gather information regarding different career options, the eligibility criteria, the premier institutions/Schools, and other criteria of selection and the market demands. The present system undertaken by Education Department, on different educational and vocational courses available and the institutions through competitive examination after 10th and 12th aims at giving you the much needed information.
INTRODUCTION
OUTLINE OF THE PROJECT
Two imperatives for better use of data confront higher education. The first is driven by external factors while the second is driven internally by continuous quality improvement. Steep declines in financial and public support have driven efforts by governments to collect data that support the proposition that
institutions are accountable for the revenue they receive. Working from a defensive posture, many colleges and universities have been able to waylay undesirable changes by satisfying external requests for data. At a higher level, however, those institutions that deliberately use data to improve overall performance meet compliance-based requirements while enacting a future that is informed by data. The proposition that higher education’s approach to data use has changed very little may be disputed. At the same time, it also is clear that technology has made new conversations possible. New techniques
including analytics or predictive analytics provide institutions new opportunities to use data to improve their efficiency while better serving students (see, for example, Bichsel, 2012 and WCET, n.d.). Colleges and universities are entering an era in which strategic information about student learning and success, budgeting, and efficiency can be united under the umbrella of big data. Higher education is now collecting more data than ever before. However, these efforts are most often directed at the first imperative, compliance reporting, rather than the second imperative, improving institutional strategy. Forward thinking institutions will quickly resolve this seeming dichotomy. They will seek opportunities to build capacity, remove constraints to span existing boundaries that determine data use and find ways to bring data and strategy together. The result can advance institutional mission, meeting external policy demands and improving student success. Strategic thinking and the data that serve those strategies come at a price. In this chapter, we review both opportunities and barriers associated with creating and using actionable strategic and operational data. We also identify successful steps for data use based on our experiences in working with higher education institutions to facilitate strategic planning and to create cultures of inquiry and evidence. We also survey emerging technologies and their promise to help institutions help their students. This chapter is intended to provide practical advice and not to provide a theoretical overview of the tenets of strategic planning. Institutions sufficiently courageous to engage in a data journey require support. Toward that end, this chapter also provides advice drawn from personal experience and new developments in management science to help navigate these new pathways.
