Level: Beginner
Poker is a very popular form of gambling, whether played at a casino or with family and friends.
Most poker players, except for professionals, lose their precious money and chips because they do not use proper logic based on probability. In this presentation, we will introduce the probability of poker, which can be seen from the fact that the relative ranking of matching patterns is slightly lower with a partial deck compared to a full deck, using a poker game that uses 16 AKQJ cards (Ace, King, Queen, Jack) from a partial deck and can be played by up to six players. We derived a generalized formula for the matching probability by using a combination formula for each possible matching pattern outcome. This poker game using a partial deck was born from the desire to simplify the simulation probability of game outcomes, and for high-ranking pattern outcomes such as "full house" (which also uses regular poker hands in this game), we were able to significantly improve the matching probability. In this AKQJ game, the winning patterns are the following "four of a kind", "full house", "three of a kind", and "two pair". When six players are playing, this AKQJ game simply calculates the regular poker probability to inform the timing of bets, making it a very exciting game that reduces emotional ups and downs when the risk is high. To study the personality and psychology of players, each player is assigned different playing characteristics based on their risk-taking tendencies. To plot the distribution of winning probabilities, we utilize JMP visualization platforms such as Graph Builder and Distribution. The game data of real players are compared to the simulated probabilities by JMP's "Hypothesis Proportion Testing". By participating in the AKQJ game, which combines statistical outcome estimation and psychological risk-taking, the results by real players are supported by worst-case probability (Monte Carlo) simulation, helping card players avoid the disease of gambling disorder by knowing the structure to play their hands in a more rational, data-based way.
To date, he has worked in the fields of hard disk drives, automotive, healthcare, medical devices, and semiconductors, implementing MBB, continuous improvement, and "JMP Transformation leader functions."
from National Taiwan University and a PhD from the University of California, Berkeley, both in Engineering. He has published over 30 technical papers, received 12 U.S. patents, and 14 ASQ certificates. He also teaches biostatistics, business statistics, data mining, big data, DOE, reliability planning, and organizational leadership.
