Estimation of Skill Distribution from a Tournament

Authors: Ali Jadbabaie, Anuran Makur, Devavrat Shah

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We apply our algorithm to various soccer leagues and world cups, cricket world cups, and mutual funds. We find that the entropy of a learnt distribution provides a quantitative measure of skill, which in turn provides rigorous explanations for popular beliefs about perceived qualities of sporting events, e.g., soccer league rankings. Finally, we apply our method to assess the skill distributions of mutual funds. Our results shed light on the abundance of low quality funds prior to the Great Recession of 2008, and the domination of the industry by more skilled funds after the financial crisis.
Researcher Affiliation Academia Ali Jadbabaie Department of CEE Massachusetts Institute of Technology Cambridge, MA 02139 jadbabai@mit.edu Anuran Makur Department of EECS Massachusetts Institute of Technology Cambridge, MA 02139 a_makur@mit.edu Devavrat Shah Department of EECS Massachusetts Institute of Technology Cambridge, MA 02139 devavrat@mit.edu
Pseudocode Yes Algorithm 1 Estimating skill PDF Pα using Z. Input: Observation matrix Z [0, 1]n n (as defined in (2)) Output: Estimator b P : R R of the unknown PDF Pα
Open Source Code No The paper mentions utilizing "publicly available data from Wikipedia" and data from the "CRSP US Survivor-Bias-Free Mutual Funds Database", but does not provide a link or explicit statement about the availability of the authors' own source code for their proposed method.
Open Datasets Yes We utilize publicly available data from Wikipedia for international (ICC) Cricket World Cups held in 2003, 2007, 2011, 2015, and 2019. ... Again, we use publicly available data from Wikipedia for FIFA Soccer World Cups in 2002, 2006, 2010, 2014, and 2018. ... Yet again, we use publicly available data from Wikipedia for the English Premier League (EPL), Spanish La Liga, German Bundesliga, French Ligue 1, and Italian Serie A in the 2018-2019 season. ... Our final experiments are calculated based on data obtained through [49] from CRSP US Survivor-Bias-Free Mutual Funds Database that is made available by the Center for Research in Security Prices (CRSP), The University of Chicago Booth School of Business.
Dataset Splits No The paper discusses the datasets used and data processing steps like Laplace smoothing, but it does not specify any explicit training, validation, or test dataset splits (e.g., 80/10/10 split, k-fold cross-validation, or specific sample counts for splits).
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory, or cloud instances) used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., programming language versions, specific library versions, or solver versions).
Experiment Setup Yes In all our simulations, we assume that η = 1, use the Epanechnikov kernel KE, and set the bandwidth to h = 0.3n−1/4; indeed, h is typically chosen using ad hoc data-driven techniques in practice [5, Section 1.4]. ... To allow for regularization in the small data regime, we apply Laplace smoothing so that between any pair of players, each observed game is counted as 20 games, and 1 additional win is added for each player; this effectively means that p = 1.