1. Introduction - IJRAR



CAMPUS PLACEMENT PREDICTION USING DATA SCIENCE1Ankita Mahalle, 2Divisha Samrit, 3 Nishigandha Wagh, 4Rucheeka Gothe1Student, 2 Student, 3 Student, 4 Student1Computer Technology, 1K.D.K.C.E, NAGPUR, INDIA.________________________________________________________________________________________________________Abstract : Placement of students is one of the most important objectives of an educational institution. Students academic achievement and their placements in companies selection is a difficult issue in the current manual system. Reputation and yearly admission of an institution is dependent upon the placement chances of a student. It also improves the placement percentage rate. The objective of the project is to analyze previous year’s dataset and predict the capability of the current year students. According to their performance the study used Na?ve Bayes, Decision Tree and Random Forest Algorithm to build the prediction model for placement of students. The model is build by both training and test set which gives accuracy in prediction. Index Terms - Na?ve Bayes, Decision Tree, Random Forest, Dataset, Data Science. _________________________________________________________________________________________________________________1. Introduction : Campus placements in institutions is an important measure for evaluation of an institution data science a multidisciplinary sector which involves scientific methods, processes, algorithms, and system remove knowledge and insights from structured and unstructured data. The success of the college is measured by the campus placement of the students. All students took admission in the college by seeing the percentage of placements in the college. Campus placement prediction and analyze help to build college as well as students to improve their placement. For prediction and analyze campus placement we used data science. Data science is the study of data. Data science predicts the accuracy with the help of machine learning and artificial intelligence. To check the probability of undergrad students getting placed in accompanying by apply classification algorithms such as ID3, random forest, decision tree. To predict the student placed or not on campus derive. This predicts based on student percentage, backlogs, CGPA, credits etc.2. RESEARCH METHODOLOGY:The whole approach depicted by the following flowchart,Data Gathering Interpretation and EvaluationPreprocessing and CleaningProcessed Data Fig: METHOD2.1. Data collection: Data collection is a process of gathering information on particular variables in an validated system which then?helps one to answer a relevant question and assess outcomes. The sample data has been collected from training and placement department which consist of all the records of previous year students. The primary goal of any data collection endeavor is to capture the quality of data.2.2. Preprocessing and Cleaning: Data preprocessing is the first step towards building a data science model. It is a technique that is used to convert the raw dataset into a clean dataset. Whenever?the data is gathered from different resources it is gathered in raw?format which is not feasible for the analysis. Therefore certain steps like data cleaning, data integration, transformation, and reduction are executed to convert the data into a clean data set.2.3. Processing: Processing is a method in which different algorithms applied on data to find the best results2.3.1. ID3 Algorithm: The ID3 algorithm is used by training on a dataset to produce?a decision tree which is stored in memory.The algorithm repeatedly divides all the attributes into two groups that are the most dominant features and others to construct a tree. Then, it calculates the entropy and information gains of each attribute. In this way, the most dominant features can be found.? Entropy: ∑i=1-P*log2(Pi)Since, the basic version of the ID3 algorithm deals with various cases where classification can be either positive or negative we can define entropy.Entropy(s) = -P+log2P+-P-log2p-Where ,S is a sample of training examples.2.3.2. Random forest tree: A large number of relatively uncorrelated models (trees) operating as a committee will outperform any of the individual constituent models. The?more number of trees in the forest?the more vigorous the forest looks. In the same way?higher the number?of trees in the forest gives?the higher accuracy.Random forest algorithm follows the following pseudo-code:1.??????Takes the?test features?and uses the rules of each created decision tree to foretell the outcome and stores the outcome.2.??????Calculate the?votes?for each predicted target.3.??????Consider the?high voted?predicted value as the?final outcome?from the random forest algorithm.Each random forest will predict a different target (outcome) for the same test feature. Then by considering each predicted target votes will be calculated.The Advantages of a random forest algorithm are as follows:?Accuracy?Handles thousands of input variables without variable deletionGives estimates of what variables are important in the classificationRuns efficiently on large databases?RESULTS AND CONCLUSION:This system is beneficial for institutions to predict student's campus placement and placement officer can work on identifying the weakness of each student. They can also suggest improvements so that the student can overcome the weakness and perform to the best of their abilities. Algorithms like random forest and ID3 will give accuracy to the prediction.ACKNOWLEDGMENT:The authors will like to thank K.D.K.C.E. for giving the student data for creating the dataset to do the research and development and also the reviewers for their constructive comments.References:[1]. Pothuganti Manvitha,Neelam Swaroopa,"Campus Placement Prediction Using Supervised Machine Learning Techniques" International Journal of Applied Engineering Research ISSN 0973-4562 Volume 14,issue 2019.[2]. Mangasuli Sheetal B, Prof. Savita Bakare “Prediction of Campus Placement Using Data Mining AlgorithmFuzzy logic and K nearest neighbour” International Journal of Advanced Research in Computer and Communication Engineering Vol. 5, Issue 6, June 2016.[3]. Ajay Shiv Sharma, Swaraj Prince, Shubham Kapoor, Keshav Kumar “PPS-Placement prediction system using logistic regression” IEEE international conference on MOOC,innovation and Technology in Education(MITE), December 2014.[4]. Jai Ruby, Dr. K. David “Predicting the Performance of Students in Higher Education Using Data Mining Classification Algorithms - A Case Study” International Journal for Research in Applied Science & Engineering Technology (IJRASET) Vol. 2,Issue 11,November 2014. ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download