• The motive to select this topic is to promote online education service businesses like Udemy, Coursera, Unacademy etc. • Students nowadays are becoming target of huge mass distraction due to Instagram and Snapchat like applications and are losing their focus on not only academic but also their respective technical domain skills. • Our goal is to indirectly increase the business of such educational platforms that make students experienced in terms of theoretical and most importantly practical knowledge. • As you will be seeing next in the presentation about how students who have selected their courses and have done better performance in their exams than students who didn’t registered for any course. • Additionally, we have compared the student’s performance based on several various factors based on upon their family education, student’s daily diet, gender based mining etc.
• Gender: Gender of Student • Race/Ethinicity: to which race or ethnicity student belongs. According to our dataset, its divided into 5 groups of race/ethnicity • Parental Education: Education of parents like mentioned in image • Student’s Diet: Here diet is divided into standard and reduced/free. • Course material: Courses registered by students • Scores: Scores in basic terminologies like reading, writing and score in maths
Target Variables: Target Variables are those variables that display feature of a dataset about which you want to gain a deeper understanding In our Dataset, target variable or field is Scores. Scores is the only target variable where we are intentionally focused. Predictor Variables that we have used in the dataset are • Race/Ethnicity • Course material • Parent’s education • Student’s diet. We are using Kmeans clustering to classify the dataset based on our predictor variables used in the dataset. For classification, we have used the features "parent_education", "lunch" and “course" which are labeled by numbers and then we classify the dataset using Kmeans algorithm.