Automatic Student Analysis and Placement Prediction using Advanced Machine Learning Algorithms
Kachi Anvesh1, B. Satya Prasad2, V. Venkata Sai Rama Laxman3, B. Satya Narayana4

1Kachi Anvesh, Assistant Professor, Department of IT, Vardhaman College of Engineering, JNTUH, Hyderabad, India.
2B Satya Prasad, Student, pursuing final year, Department of IT, Vardhaman College of Engineering, JNTUH, Hyderabad, India.
3Venkata Sai Rama Laxman, Student, Pursuing final year, Department of IT, Vardhaman College of Engineering, JNTUH, Hyderabad, India.
4B Satyaarayana, Student, pursuing final year, Department of IT, Vardhaman College of Engineering, JNTUH, Hyderabad, India.

Manuscript received on September 18, 2019. | Revised Manuscript received on 24 September, 2019. | Manuscript published on October 10, 2019. | PP: 4178-4183 | Volume-8 Issue-12, October 2019. | Retrieval Number: L36641081219/2019©BEIESP | DOI: 10.35940/ijitee.L3664.1081219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The amenable statement with respective to Company Organization, Institution and students is that the company organization are taking more time to recruit which is a big challenge to them and there is no specific platform to recruit candidates on preferred qualifications. The Institutions are unable to get 100% placements among eligible students.The institutions doesn’t provide proper training on minimum and preferred qualifications to the students. The candidates are unable to get specific training from college organization. The college organization should provide the training to candidates at what they are lagging behind and make the students to get stronger in preferred qualifications and all other aspects. “52% of Talent Acquisition leaders say the hardest part of recruitment is screening candidates from a large applicant pool”. The time spent on screening students from a large pool often takes up the largest portion of the time. Despite College Organization are also not training students effectively based on company requirements. The analysis of student is to be done to know where the student is failing to get the placement. The company doesn’t know the personalityof the student while recruiting the students. To solve this bottleneck in recruiting we created this automation tool. The main process of determining whether a candidate is qualified based on minimum qualifications like CGPA, Certifications, Projects done, Internships and respectively. There are two main goals of this project are: 1. To decide whether to move the student forward to an interview or to reject them. 2. The college organization can give more training to the students those who got rejected by small issues like communication, programming, aptitude… This process is based on minimum qualifications and preferred qualifications. Both types of qualifications are more useful to the recruiters. These qualifications can include experience on projects, education, skills and knowledge, personality traits, competencies. The minimum qualifications are the mandatory qualifications that the company organizations required and preferred qualifications are not mandatory but to make the student stronger from other students. The personality and also technical knowledge can be given accurately by the faculty, mentor, H.O.D Based on the qualifications, personality analysis, we can shortlist the students and proper analysis is done. So the recruiters don’t spend more time and college scan improve their placement percentage to 95% by improving more skills of the students, improving skills who are lagging behind (not short listed). The colleges can predict how many students are going to be placed and who are needed to be trained more. The students can evaluate themselves about their suitable job role which make organizations easy to give job role to the students. This paper mainly concentrates on the career area prediction of computer science domain candidates.
Keywords: Machine learning, Data Science, prediction, Training, Testing, SVM, XG Boost, Decision tree, Logistic Regression, OneHot Encoder.
Scope of the Article: Machine learning