Evaluation of Team’s False ‘9’ for Match Winner Prediction

Abstract

The quest to develop a concrete analysis on evaluation of teams false
‘9’ for match winner prediction depends on the predictability of
match results. The main concern of this research is on the efficiency
of team manager tactics that deals with the usage and feeding of false
‘9’ position in the football tactics used for a match. The effect of the
false ‘9’ role in match prediction was also evaluated. The recent
applied statistics literature has focused primarily on modelling goal
scoring. The prediction of the match depends on variables like team
statistics, historical data etc. which is used by managers and club
directors to decide who is going to win the match and what is needed
to win the match but football result prediction has gained lots of
popularity in recent years due to sports betting markets. A manager’s
tactics is now being used to develop a football match result predictive
model by gathering the features that affect the outcome of football
matches. Data extracted from site and their features (Attacking,
Tackling, Technicality, Creativity and Defense) were used to
compute the metric values of the prediction. Support Vector Machine
(SVM) algorithm was used in prediction of team’s performance using
false ‘9’ abilities to determine winning for the team. The system
structure and the visible activities that take place within the system
were also presented using appropriate design. The support vector
machine system was implemented using Python as the software tool.
The performance of the SVM is used to ascertain the level of
accuracy of the prediction. Though many soccer predictive works
have been done, this study was able to establish a prediction model
using Support Vector Machine (SVM) algorithm for the evaluation
of match winning considering false ‘9’ roles, which is the first
predictive model from that angle/specific aspect of football
prediction and was able to give a 97% accuracy