Produce101 analysis and estimate with the Machine Learning
0 likes531 views
This document analyzes and estimates the results of the Korean TV competition show "Produce 101" using machine learning. The analysis was able to predict the final results with over 80% accuracy. Key factors in predictions included beauty, agency fame and expectations, and amount of exposure on TV from early episodes. The analysis recommends buying stocks in agencies that had many winners.
Produce101 analysis and estimate with the Machine Learning
- 1. P R O D U C E 1 0 1 A N A LY S I S & E S T I M AT E B Y S A M K U G J I 1
- 2. C o m p e t i t i o n T V s h o w ‘ P r o d u c e 1 0 1 ’ f i n a l r e s u l t e s t i m a t i o n ( p r e d i c t i o n ) w i t h m a c h i n e l e a r n i n g m o r e t h a n 8 0 % s u c c e s s 2
- 3. W H AT ? • Estimate future (6 weeks) 3
- 4. W H Y ? • Business Insight • Difficult • Interesting 4
- 5. H O W ? • Machine Learning • OLS (Ordinary Least Squares) • See what I do • Control what I do • Interpret what I do 5
- 6. 6
- 7. B U S I N E S S I N S I G H T • Beauty is the one of powerful factor • Agency’s fame and expectations • Don’t miss Time of exposure on TV from the episode 1 • The number of persons per a agency is limit to 2 persons 7 BUY STOCKS of agencies has 11 winners (Fantagio 94% up , JYP 10% up)
- 8. A C C U R A C Y F O R F I N A L I D O L I N 9 4 G I R L S 8 1 . 8 1 % 9 0 . 9 0 % A C C U R A C Y F O R F I N A L A G E N C Y I N 4 8 A G E N C I E S 8
- 9. I ’ M S A M K U G J I • https://github.com/ samkugji • https:// www.linkedin.com/in/ samkugji • DS(Dae-Sung) Yu • DS(DataScientist) • DS(Definite Sixth-sense) 9