The Research Team of Professor In-Jung Kim of the School of Computer Science and Electrical Engineering, Handong Global University succeeded to commercialize the first T-Commerce Program Management System using Deep Learning. T-Commerce is a term describing trade via a smart digital TV-set which acts as a marketing channel enabling bi-directional communication.
In order to maximize the profit of T-Commerce it is important to assign split-timed competitiveness to each product. This is important since channel numbers and products are limited.
So far, the T-Commerce Program Management System is highly dependent on the experience and individual judgement of the program organizer. However, the Research Team of Professor In-Jung Kim of HGU forecasts profits in T-Commerce by using Deep Learning and by developing algorithms to organize maximized profit programs automatically. These programs will be applied to W Shopping corp., the operators of T-Commerce.
According to the Director of W Shopping Corp., Mr. Dukjung Kim, “The profits of T-Commerce and Home-shopping are varied depending on the program organization during a 24 hour period. Just like AlphaGo required learning lots of prior information and patterns of Go, the computer learns previous sales information, and weather information through deep learning. It can organize optimize programs by forecasting product sales and time based profits.
Professor In-Jung Kim said, “In the world, Korea is one of the leading countries in terms of T-Commerce. This is the first case using the T-Commerce Broadcasting Program Management System commercially based on Machine Learning technology, in the world.”
The Research Team of Professor In-Jung Kim of Handong Global University consisted of Professor Haebobg Choi, and eight undergraduate school students including: Keehyun Na, Sohee Yang, Jaemin Chang, Yoonjong Kim, Wonyeong Shin, Jinhyuk Yang, Hyukmin Kwon, and Hyoeun Kim.
※ Terminology
Deep learning (also known as deep structured learning, hierarchical learning or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high level abstractions in data.
Machine learning is the subfield of computer science that gives computers the ability to learn without being explicitly programmed. This has evolved from the study of pattern recognition and computational learning theory in artificial intelligence. Machine learning explores the study and construction of algorithms that can learn from and make predictions based on data.
