\nMy analysis is thoroughly documented in the following sections:
\n\n - Background and Conclusion\n - Methodology\n - Analysis\n - Qualifications\n\n"},{"metadata":{},"cell_type":"markdown","source":"\n
The National Football League (NFL) is a professional American football league consisting of 32 teams, divided equally between the National Football Conference (NFC) and the American Football Conference (AFC). The NFL is one of the four major professional sports leagues in North America and the highest professional level of American football in the world.\n\nRecent investigations of lower limb injuries among football athletes have indicated significantly higher injury rates on synthetic turf compared with natural turf (Mack et al., 2018; Loughran et al., 2019). In conjunction with the epidemiologic investigations, biomechanical studies of football cleat-surface interactions have shown that synthetic turf surfaces do not release cleats as readily as natural turf and may contribute to the incidence of non-contact lower limb injuries (Kent et al., 2015).\n\nFew of the key observations noted from Turfgrass Producers International based on games played in between 2012-16 are :\n\n* 1,280 NFL games (213,935 distinct plays) were played during the 2012-16 seasons.\n* 4,801 lower body injuries occurred during the study sample, affecting 2,032 NFL players.\n* Synthetic turf resulted in a 27% increase in non-contact lower body injuries.\n* 56% higher rate (knee/ankle/foot) of sustaining an injury on synthetic turf that resulted in time lost, and a 67% higher injury rate resulting in more than 8 days time lost from injury.\n* 68% higher rate of sustaining an ankle injury rate on synthetic turf that resulted in any time lost from injury and a 103% increase in injury rates on synthetic turf resulting in more than 8 days time lost from injury."},{"metadata":{},"cell_type":"markdown","source":"\n
I followed an in-depth approach using statistical methodolgies to arrive at conclusion and tested multiple types using sampling of the given data to ensure that there is no biasness in the observations noted. I have also tried to utilize classification models - SVM and Random Forest, however the data provided didn't bring any acceptable model significance and dropped the model and went ahead with Exploratory Data Analysis. I have tried to keep my analysis simple, yet detailed so that it can be easily understood by anyone reading them
\n\nThe entire analysis was built on sample comparison to check the biasness due to the presence of less injury cases compared to non injury cases. Every conclusion drawn has been repeatedly validated by multiple samples.\n\nI am currently as a Principal Data Scientist with ITC Infotech Ltd with strong math background and 9+ years of experience using predictive modeling, data processing, and data mining algorithms to solve challenging business problems in Retail/CPG/BFSI domain. Involved in R/Python open source community and passionate about deep reinforcement learning and other advance ML algorithms."}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":1}