Using Soft Computing Techniques for Prediction of Winners in Tennis Matches

• DOI: 10.11648/j.mlr.20170203.12
• Publication Date: 2017-04-10
• Authors: Mateus Fernandes
• Keywords: Predictability; Competitor analysis; Soft Computing

The forecast of winners in sports brings valuable information for both organizers, media and audience, this is particularly important tennis, where the results a round tournament determine which matches will occur next round. With that mind, work presents study main factors influencing predictability and, from analysis, new hybrid approach proposed to calculate chances victory each competitors before start match. A Fuzzy Inference System, with its ability reproduce knowledge an expert among mixed information, Neural Network, capability features extraction examples, Strength Equation optimized weighting are techniques employed. These predictors have as inputs data previous performances players, case try capture their short, medium long-term performances, well affinity different types surfaces. Subsequently these combined by voting system. encouraging, showing significant gains when comparing use ATP ranking.