Who will get the diploma?
Problem being addressed
With the recent development of technology such as digital video processing and live streaming, there has been a steady increase in the amount of K-12 (kindergarten to 12th grade) students studying online courses worldwide. In spite of the advantages of this new learning opportunity, K-12 students usually fail to finish online course programs with little supervision from either their parents or teachers.
A novel approach that considers both online and offline factors around K-12 students and aims at solving the challenging problems of (1) multiple modalities, i.e., K-12 online environments involve interactions from different modalities such as video, voice, etc; (2) length variability, i.e., students with different lengths of learning history; (3) time sensitivity, i.e., the dropout likelihood is changing with time; and (4) data imbalance, i.e., only less than 20% of K- 12 students will choose to drop out the class.
Advantages of this solution
In the offline experiments, the method improves the dropout prediction performance when compared to state-of-the-art baselines on a real-world educational data set. In the online experiments, the approach is tested on a third-party K-12 online tutoring platforms for two months weeks and the results show that it is able to achieve that more than 70% of the dropout students are detected by the system.
Solution originally applied in these industries
Possible New Application of the Work
HR managers can adopt this approach to predict burnout among employees, which will help them improve the wellbeing of the people as well as save huge expenses for the employer.
The suggested approach analyses multiple modalities, length variability, time sensitivity and data imbalance problems, and it as well, with adequate adjustments, be used to predict customer churn and customer lifetime value.
Source URL: #############