Sports Analytics Video – Convolutional Neural Networks

In this installment of Victor Holman’s Sports Analytics 3 Minute Drill, Victor explains Convolutional Neural Networks. In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery. Convolutional Neural Networks use a variation of multilayer perceptrons designed to require minimal preprocessing. They are…

Details

Sports Analytics Video – Conditional Probability

In this installment of Victor Holman’s Sports Analytics 3 Minute Drill, Victor explains conditional probability. Conditional Probability. Probability is defined as a measure of how often a particular event will take place if the experiment occurs repeatedly. Probability ranges from zero to one.  Zero indicates that the event is impossible, and one indicates that the…

Details

Sports Analytics Video – Boruta Algorithms

In this installment of Victor Holman’s Sports Analytics 3 Minute Drill, Victor explains boruta algorithms. Boruta is an all relevant feature selection wrapper algorithm, capable of working with any classification method that output variable importance measure (VIM); by default, Boruta uses Random Forest. The method performs a top-down search for relevant features by comparing original…

Details

Sports Analytics Video – Strategy and Match Modelling

In this installment of Victor Holman’s Sports Analytics 3 Minute Drill, Victor explains Strategy and Match Modelling. This is a review of the team strategy model and match model research conducted by Leonardo Lamas, Junior Barrera, Guilherme Otranto and Carlos Ugrinowitsch. ———————- Find out how Sports Analytics Expert Victor Holman can give your team the…

Details

Sports Analytics Video – Qualitative Exploration

In this installment of Victor Holman’s Sports Analytics 3 Minute Drill, Victor explains qualitative exploration. Probably the oldest of all scientific techniques, qualitative exploration is a method used extensively by scientists, researchers and analysts to study human behavior, opinions, themes and motivations. Different from quantitative data, which relates to quantities, amounts and measurements that can be…

Details

Sports Analytics Video – Spatio Temporal Trajectory Clustering

In this installment of Victor Holman’s Sports Analytics 3 Minute Drill, Victor explains spatio-temporal trajectory clustering. Spatio-temporal trajectory clustering methods identify heterogeneous patterns and explore underlying mechanisms and are designed to consider both temporal and spatial information in trajectories. Applying the time-dependent shortest-path distance measurement and taking advantage of topological relations of a predefined network,…

Details