Browsing by Author "Masika, Robert"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Classification Algorithm for Career Recommendation System
    (International Journal of Computer Applications Technology and Research, 2022-04-10) Masika, Robert; Rono, Richard; Kati, Robert O.
    The tremendous developments in technology that have been realized in this digital era have greatly improved the way in which data is collected and used in schools. Over the years the number of secondary schools using technology in processing student data has been increasing steadily. As a result, a large amount of data in electronic form has been gathered. Classification algorithms can be used to study the patterns presented in these data and use it to predict a suitable career for a student. In this study classification algorithms were used to predict a suitable career for form four students. The study evaluated the best classification algorithm for implementing the career recommendation system in Kenya. The Cross Industry Standard Process for Data Mining framework was applied to a dataset drawn from form four students in Bungoma County in Kenya. Stratified random sampling was used to select 50 secondary schools and a 10% of candidates were selected from every sampled schools. The collected data were cleansed, preprocessed and analyzed using a data mining tool of RapidMiner. Various classification algorithms were evaluated in predicting a suitable career for a student. The study findings revealed that classification algorithms can be used to predict a suitable career for a student. All the classifiers that were used gave a predictive accuracy of above 88% though deep learning was the most accurate with 97.5%. However, since the classifiers out performed each other in various metrics, therefore using multiple classification algorithms in building the recommendation model can yield better results. The study therefore concludes that classification models comprising of multiple classifiers can be used to predict suitable careers for secondary students.
  • No Thumbnail Available
    Item
    Extent Of Usage of Collected Student Data in Career Choice in Kenya
    (Iconic Research and Engineering Journals, 2021-12-10) Masika, Robert; Rono, Richard; Kati, Robert O.
    This study investigated the extent to which student data collected in secondary schools in Kenya is used in career choice. After admission in form one, a student undertakes a four-year study program and at the tail end selects a career to pursue later. During the admission process and throughout their stay in the school, a lot of student data is usually collected and stored either in the school database, in students’ files kept by various departments and/or in the online platforms e.g., National Educational Management Information System (NEMIS) etc. However, it is possible to collect data and fail to use it to guide decision making and this can result in wastage of a precious asset of these institutions. The population of the study ere career masters/mistresses and deputy principals in charge of academics. Stratified random sampling was used to select 50 secondary schools and a sample of 60 participants. The collected data were analyzed using descriptive statistics using frequency tables. The study findings revealed that schools do keep data on family background, career aspiration and academic data but leave out data on student personality and job opportunities which are key drivers of career choice. The most common data in secondary schools is academic data (65%) which is majorly used to guide learner progress (77.5%). This data is mainly collected during continuous assessment (57.5%) and is kept under the custody of the director of studies (52.5%). Though majority of the respondents (85%) believed that data collected has an effect on the student career choice, it was noted that the available student data isn’t used directly to guide career choice. This is because most of the collected data is stored in offline storage systems which limit access. However, majority respondents (95%) believe that data collected can help improve student career choice. The fact that inadequate data is collected and it isn’t accessed easily then it follows that the decisions made in the school aren’t based on fact. The study therefore concluded that there is low usage of student data in career choice. The study recommends that secondary schools should ensure that comprehensive student data is collected and stored in portable formats to increase access and usage. This data should form the basis for career choice by the students. This finding will help to enhance student data collection in schools which in turn will improve the career decision making leading to appropriate career choices.