Cricket Score Prediction Using Machine Learning

Currently, there is a system which can calculate the current run rate and from it calculates the final score of the team. It doesn’t consider the fact about the no of wickets and also where the game is being played. The problem with the current system is that it is unable to predict the score of the 2nd team and also unable to predict the win percentage This system which is developed will have 2 model in it the 1st model predict the score a team will get after playing 50 over from the current situation. The second method predicts the win percentage of both teams even before the match has started this done by player selection. We found that error in regression toward the mean classifier could be a smaller quantity than Naïve mathematician in predicting match outcome has been sixty-eight ab initio from 2-15 overs to ninety-one until the top of 42th over.

PENGGUNAAN METODE PROFILE MATCHING DAN NAÏVE BAYES UNTUK MENENTUKAN STARTING ELEVEN PADA SEPAK BOLA

Abstrak - Pemilihan pemain starting eleven atau kesebelasan dan formasi tim dengan komposisi pemain yang tepat dalam olahraga sepak bola merupakan hal yang penting untuk meningkatkan performa permainan sebuah tim. Pelatih terkadang memilih pemain starting eleven tidak secara objektif, dikarenakan dibutuhkan keahlian dan kejelian dalam menilai kemampuan seseorang. Guna memudahkan pemilihan pemain dalam starting eleven maka dibangun sistem untuk membantu pelatih memilih posisi I deal bagi pemain dan memilih pemain secara objektif agar meningkatkan kualitas pemilihan pemain, baik dari penempatan posisi ideal pemain maupun pemilihan pemain sebagai starting. Sistem ini akan menerima input berupa nilai atribut kemampuan dan kondisi pemain yang akan diproses untuk menghasilkan output berupa rekomendasi pemain untuk dijadikan starting eleven. Dalam proses menentukan pemain, nilai atribut kemampuan pemain dilakukan proses Profile Matching (PM) untuk menentukan posisi ideal bagi pemain, dari tiap kelompok posisi dilakukan proses identifikasi menggunakan Naïve Bayes (NB) untuk menentukan pemain yang cocok untuk dijadikan starting eleven. Pengujian rekomendasi posisi dilakukan dengan membandingkan posisi asli pemain dengan posisi hasil rekomendasi dengan hasil akurasi sebesar 65%, sedangkan pengujian pemilihan starting eleven dilakukan menggunakan game Football Manager dengan melakukan pertandingan dengan pemilihan pemain secara default dan pemilihan pemain hasil rekomendasi masing-masing sebanyak sepuluh kali melawan tim dengan komposisi pemain yang sama, hasil dari pertandingan tersebut dihitung selisih (%) dari rata-rata rating pemain. Hasil yang diberikan setelah digunakan perekomendasian pemilihan pemain kenaikan rata-rata rating tim hanya naik sebesar 0.98%. Abstract - The selection of starting eleven players and team formations with the correct composition of players in soccer is important to improve the performance of a team. Coaches sometimes choose not starting players objectively, because it takes expertise and foresight in assessing one's abilities. In order to facilitate the selection of players in the starting eleven, a system was built to help the coach choose the ideal position for the players and choose players objectively to improve the quality of player selection, both from placing the player's ideal position and selecting players as starting. This system will receive input in the form of the ability and condition attribute values ​​of the player which will be processed to produce output in the form of a player's recommendation to become the starting eleven. In the process of determining the players, the value of the attributes of the player's ability is carried out the Profile Matching (PM) process to determine the ideal position for the players, from each group of positions the identification process is done using Naïve Bayes (NB) to determine the suitable players to be the starting eleven. Position recommendation testing is done by comparing the original position of the player with the position of the recommended results with an accuracy of 65%, while testing the selection of the starting eleven is carried out using the game Football Manager by playing matches by selecting players by default and selecting the results of the recommendation players ten times each against the team with the same player composition, the result of the match is calculated as a difference (%) from the average player rating. The results given after using the player selection recommendation increase the team's average rating to only increase by 0.98%.

Cricket Player Selection using Machine Learning

Cricket has always been a popular game since its invention in the world. Moreover, it became a religion in India. The selection committees like BCCI,PCB,ACB etc. pick the players based on their previous performances in domestic cricket tournaments like IPL,Ranji Trophy, Syed Mushtaq Ali Trophy etc. by committee decisions but there is no application for selection process till now. To develop an application we need player performance analysis and assessment. This paper suggests an important approach for Selecting Cricket players by Evaluating his Statistics and Provides a comparative look at machine learning techniques in cricket player selection. In this paper a model for Bowlers and Batsmen Separately was proposed which was implemented using Random Forest, AdaBoost, Support Vector Machines(SVM), LightGBM,CatBoost, Logistic Regression Linear Discriminant Analysis(LDA), Voting Classifier, Naïve Bayes. The findings obtained by the suggested methodology in this paper are the same as in the Cricket board selected team players.