data_viz_group6

Data Visualization Assignment Submission for MAM 2024 Group6

At Star-In-Making, we are committed to harnessing the power of data analytics to guide emerging strikers in selecting the optimal team to commence their professional careers. We recognize the significance of the initial step in shaping their global brand and leading the scoring charts in competitive leagues. Understanding the nuances of European football's competitive environment, we emphasize the importance of a well-suited match between a player's attributes and a league's characteristics. For instance, a league with a reputation for physicality may not be the ideal setting for a player with less physical prowess.

To address this, Star-In-Making has developed a methodological approach based on historical data analysis to assist strikers in making well-informed decisions. Our methodology encompasses a three-fold strategy:

1. Identifying the most suitable league for a striker's skill set and playing style.
2. Determining the teams that provide the best opportunities for goal scoring.
3. Analyzing potential team members whom they might effectively replace.

While our approach takes into consideration a multitude of variables, it adheres to the Pareto Principle (80/20 rule), ensuring that it serves as an efficient and pragmatic first step in the decision-making process.

The methodology is successful is quickly evaluating a potential career for a young striker to join a team. It effectively breaks the problem into three aspects: league, team and player to narrow down to the best option for him to succeed. Our recommendation is also in line with the present, as Dortmund is known as a birthplace of European football legends, and Erling Halland and Jordan Sancho both shifted clubs at a high price. This indicates that Marco Reus was the weakest player, also the most potential to be switched by our striker.

Star-In-Making's analytical framework is underpinned by a comprehensive database comprising seven distinct but interconnected data sets. These datasets are meticulously linked through key identifiers: League ID, Player ID, and Game ID. This extensive repository encompasses detailed match-level data from five major European leagues, spanning a period from 2015 to 2021.

Data Sources:

1. https://github.com/statsbomb/open-data/tree/master
2. https://www.kaggle.com/datasets/technika148/football-database/

Our approach is not only retrospective but also forward-looking. By leveraging historical data, we aim to validate our recommendations against the current European standings and the real-time performance of the players we suggest as potential replacements. This method ensures a robust, data-driven foundation for our recommendations, enabling us to provide strategic insights with a high degree of accuracy and relevance to the contemporary football landscape.

References:

1. https://github.com/Torvaney/ggsoccer
2. https://towardsdatascience.com/how-to-visualize-football-data-using-r-ee963b3a0ba4
3. https://jaseziv.github.io/worldfootballR/articles/extract-fbref-data.html#get-season-team-stats
4. https://github.com/statsbomb/StatsBombR