Systematic Literature Review of Prediction Techniques to Identify Work Skillset (original) (raw)
Related papers
Analyzing and Predicting Career Specialization using Classification Techniques
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Nowadays, academic institutions conduct studies to attain quality and excellence in student academic performance through Data Mining tools. This paper explores various classification techniques in predicting graduates' career specialization. The data sets used were obtained from Bulacan State University Sarmiento Campus' Information Technology graduates from 2013 to 2016. From these data, a model was created using Naïve Bayes, J48, Random Forest, and Support Vector Machine classification algorithm, with 18 attributes. Among the models built, Naïve Bayes and Random Forest algorithm yielded better accuracy rating, and acceptable ROC and RMSE values. Performance of students per subject area was also determined, and based on this; students perform satisfactorily in both soft and technical skills manifested in the highly satisfactory performance on the Internship course. However, there were few graduates who pursue a career in Networking, and measures must be undertaken to elevate performance in early Programming and Networking courses..
Classification Techniques for Predicting Graduate Employability
International Journal on Advanced Science, Engineering and Information Technology
Unemployment is a current issue that happens globally and brings adverse impacts on worldwide. Thus, graduate employability is one of the significant elements to be highlighted in unemployment issue. There are several factors affecting graduate employability, traditionally, excellent academic performance (i.e., cumulative grade point average, CGPA) has been the most dominant element in determining an individual's employment status. However, researches have shown that not only CGPA determines the graduate employability; in fact other factors may influence the graduate achievement in getting a job. In this work data mining techniques are used to determine what are the factors that affecting the graduates. Therefore, the objective of this study is to identify factors that influence graduates employability. Seven years of data (from 2011 to 2017) are collected through the Malaysia's Ministry of Education tracer study. Total number of 43863 data instances involved in this employability class model development. Three classification algorithms, Decision Tree, Support Vector Machines and Artificial Neural Networks are used and being compared for the best models. The results show decision tree J48 produces higher accuracy compared to other techniques with classification accuracy of 66.0651% and it increased to 66.1824% after the parameter tuning. Besides, the algorithm is easily interpreted, and time to build the model is small which is 0.22 seconds. This paper identified seven factors affecting graduate employability, namely age, faculty, field of study, co-curriculum, marital status, industrial internship and English skill. Among these factors, attribute age, industrial internship and faculty contain the most information and affect the final class, i.e. employability status. Therefore, the results of this study will help higher education institutions in Malaysia to prepare their graduates with necessary skills before entering the job market.
The main focus in training evaluation is not only to determine whether training objectives were achieved but also how to improve evaluation so as to enhance both employability of graduates and performance in the job. This is in response to challenges facing not only graduates in choosing industry jobs that befit their skills, but also employers in selecting graduates whose skills match to their needs. Problem solving is one of the skills acquired during training by graduates and strongly sought for by employers during evaluation to promote performance in the job. This paper presents a model for evaluating graduates' by mapping their problem solving skills to industry jobs' competence requirements and the potential of using machine learning techniques to train the model in predicting suitable industry jobs for new graduates from college. The paper outlines challenges facing both graduates and industry in selecting industry jobs and skilled graduates respectively, highlights trends, methods, and gaps in skill evaluation and prediction. A brief discussion is made of key strategies in skill evaluation and prediction that need to be undertaken and evaluation theories behind the key variables of the proposed model.
Prediction of Future Career Path Using Different Machine Learning Models
Emerging Technologies in Data Mining and Information Security, 2021
The main purpose of this paper is to examine the strength and weaknesses of a student based on their performance in different exams. Students are classified using the K-means classification algorithm and decision tree. The proposed model will help teachers to comprehend their students well and will also assist the students to get their most serviceable job. The data mining technique capable of analyzing relevant results is used over the students' information to produce relevant correlations and produce different aspects to understand more about the students. The paper proposes a model based on a classification approach in finding an enhanced evaluation method for students and predict the placement prospects.
Proposing a Machine Learning Approach to Analyze and Predict Employment and its Factors
International Journal of Interactive Multimedia and Artificial Intelligence, 2018
This paper presents an original study with the aim of propose and test a machine learning approach to research about employability and employment. To understand how the graduates get employed, researchers propose to build predictive models using machine learning algorithms, extracting after that the most relevant factors that describe the model and employing further analysis techniques like clustering to get deeper insights. To test the proposal, is presented a case study that involves data from the Spanish Observatory for Employability and Employment (OEEU). Using data from this project (information about 3000 students), has been built predictive models that define how these students get a job after finalizing their degrees. The results obtained in this case study are very promising, and encourage authors to refine the process and validate it in further research.
Machine Learning for Predicting Students’ Employability
UMYU Scientifica
Graduates' employability becomes one of the performance indicators for higher educational institutions (HEIs) because the number of graduates produced every year from higher educational institutions continues to grow and as competition to secure good jobs increases, it is significant for HEIs to understand the employability of graduates upon graduation and highlight the reasons. To predict students' employability before graduation, machine learning models were employed. These include logistic regression; decision tree, random forest, and an unsupervised clustering (K-Means) algorithm. This research, therefore, aims to predict the full-time employability of undergraduate students based on academic and experience employability attributes – including cumulative grade point average (CGPA), student industrial work experience scheme (SIWES), co-curricular activities, gender, and union groupings before graduation. Primary datasets of 218 graduate students in the last four academic ...
The Application of Data Mining to Build Classification Model for Predicting Graduate Employment
Data mining has been applied in various areas because of its ability to rapidly analyze vast amounts of data. This study is to build the Graduates Employment Model using classification task in data mining, and to compare several of data-mining approaches such as Bayesian method and the Tree method. The Bayesian method includes 5 algorithms, including AODE, BayesNet, HNB, NaviveBayes, WAODE. The Tree method includes 5 algorithms, including BFTree, NBTree, REPTree, ID3, C4.5. The experiment uses a classification task in WEKA, and we compare the results of each algorithm, where several classification models were generated. To validate the generated model, the experiments were conducted using real data collected from graduate profile at the Maejo University in Thailand. The model is intended to be used for predicting whether a graduate was employed, unemployed, or in an undetermined situation. https://sites.google.com/site/ijcsis/
Scientific Approach for Discovering Employability Skills
2020
The ability to effectively match an employee’s skills and personality to a specific job offer is a great advantage for job seekers. Currently, extraction from a textual dataset through a job advertisement has become an effective way of discovering knowledge from a given collection of vacancies. Thus, this paper attempts to determine the employer’s requirement of skills from fresh graduates with the degree in Statistics. The source of data is from an online job advertisements platform extracted from September 2019 until February 2020. Text Mining analysis and Pearson Chi-square Test were employed for the analysis. The results showed that essential hard skills for graduates are the ability to work with data and equipped with computer skills. Meanwhile, communication skills and being a multi-tasker are main soft skills required by employers. In addition, results showed that soft skills are sought differently in product-based industry and service-based industry. Results have shown some ...
Predicting Skill Shortages in Labor Markets: A Machine Learning Approach
SSRN Electronic Journal, 2020
Skill shortages are a drain on society. They hamper economic opportunities for individuals, slow growth for firms, and impede labor productivity in aggregate. Therefore, the ability to understand and predict skill shortages in advance is critical for policy-makers and educators to help alleviate their adverse effects. This research implements a high-performing Machine Learning approach to predict occupational skill shortages. In addition, we demonstrate methods to analyze the underlying skill demands of occupations in shortage and the most important features for predicting skill shortages. For this work, we compile a unique dataset of both Labor Demand and Labor Supply occupational data in Australia from 2012 to 2018. This includes data from 7.7 million job advertisements (ads) and 20 official labor force measures. We use these data as explanatory variables and leverage the XGBoost classifier to predict yearly skills shortage classifications for 132 standardized occupations. The models we construct achieve macro-F1 average performance scores of up to 83 per cent. Our results show that job ads data and employment statistics were the highest performing feature sets for predicting year-to-year skills shortage changes for occupations. We also find that features such as 'Hours Worked', years of 'Education', years of 'Experience', and median 'Salary' are highly important features for predicting occupational skill shortages. This research provides a robust data-driven approach for predicting and analyzing skill shortages, which can assist policy-makers, educators, and businesses to prepare for the future of work.
Analyses of Students’ Vocational Data Using Some Selected Classification Algorithms
Unemployment is a major issue battling the Nigerian economy. Today's trend is shifting towards skills acquisition rather than on certificate qualification which are capable of making the youths self-dependent, job creators and not job seekers (Okolocha,2012). The management of The Polytechnic, Ibadan, Nigeria is working tirelessly to ensure that each student learns a vocational skill to prepare them for entry into the labour market (Adebayo, 2016). In this study, data mining techniques were used to analyze students' vocational data of The Polytechnic, Ibadan in Nigeria to discover patterns and relationships that will help the school management to make important decisions and plan better for more productive execution of their vocational skills programme. Experiments were performed using ID3, C4.5 and Naïve Bayes classification algorithms to build models under WEKA 3.8.2 environment. Hold-out method and 10 folds cross-validation method were used to test the models. Confusion matrix was used to evaluate the performance of the models on the basis of accuracy, sensitivity and time taken to build the models and it was discovered the C4.5 algorithm gave the best performance with both validation techniques.