This study applied multiple machine learning algorithms to classify the performance levels of professional goalkeepers (GK). Technical performances of GK’s competing in the elite divisions of England, Spain, Germany, and France were analysed in order to determine which factors distinguish elite GK’s from sub-elite GK’s. A total of (n = 14,671) player-match observations were analysed via multiple machine learning algorithms (MLA); Logistic Regressions (LR), Gradient Boosting Classifiers (GBC) and Random Forest Classifiers (RFC). The results revealed 15 common features across the three MLA’s pertaining to the actions of passing and distribution, distinguished goalkeepers performing at the elite level from those that do not. Specifically, short distribution, passing the ball successfully, receiving passes successfully, and keeping clean sheets were all revealed to be common traits of GK’s performing at the elite level. Moderate to high accuracy was reported across all the MLA’s for the training data, LR (0.7), RFC (0.82) and GBC (0.71) and testing data, LR (0.67), RFC (0.66) and GBC (0.66). Ultimately, the results discovered in this study suggest that a GK’s ability with their feet and not necessarily their hands are what distinguishes the elite GK’s from the sub-elite.

No abstract

Key Performance Indicators (KPIs) have been investigated, validated and applied in multitude of sports for recruiting, coaching, opponent, self-analysis etc. Although a wide variety of in game performance indicators have been used as KPIs, they lack sports specific context. With the introduction of artificial intelligence and machine learning (AI/ML) in sports, the need for building intrinsic context into the independent variables is even greater as AI/ML models seem to perform better in terms of predictability but lack interpretability. The study proposes domain specific feature preprocessing method (normalization) that can be utilized across a wide range of sports and demonstrates its value through a specific data transformation by using team possession as a normalizing factor while analyzing defensive performance in soccer. The study performed two linear regressions and three gradient boosting machine models to demonstrate the value of normalization while predicting defensive performance. The results demonstrate that the direction of correlation of the relevant variables changes post normalization while predicting defensive performance of teams for the whole season. Both raw and normalized KPIs showing significant correlation with defensive performance (p < 0.001). The addition of the normalized variables contributes towards higher information gain, improved performance and increased interpretability of the models.

Detailed pedigree charts were prepared from 120 index patients suffering from Indian childhood cirrhosis (ICC). Of the 120 families, 84 were informative for segregation analysis. Since families were ascertained through patients who came to hospital for treatment, the data were analyzed according to a single-selection model. The observed segregation ratio for the entire data was significantly lower than the one expected under the hypothesis of autosomal recessive inheritance (p = < 0.005). On the other hand, the segregation data for families with at least two affected children (multiplex families) were compatible with autosomal recessive inheritance. On this basis, however, at least 50% of all the cases of ICC would have to be of nongenetic origin. Alternatively, analysis of the data by the Falconer method indicated that ICC could be of multifactorial origin with very strong genetic determination (over 85%).

No abstract