Data Science Projects

Apache Spark for Data Science

(January - April 2021)

(joint work with T. Abera, J. Coleman, G. Gonzales and S. McWhirter )

• This research covers the Apache Spark ecosystem, where it fits into the cloud framework, its functions underneath the hood, and machine learning examples to illustrate how the ecosystem operates. Apache Spark is a distributed computing framework that is ideal for handling big data. Spark is an ideal solution to explore, as the ability to handle big data can be a burdensome administrative task yet very necessary. This research will discuss where Spark fits into the framework of IaaS, PaaS, and SaaS, as well as its benefits and drawbacks compared to proprietary solutions. This research also provides a brief demonstration on how computing on Spark actually takes place to further illustrate its functions.

• Final report: https://hnguye01.github.io/spark.pdf

Identifying Aggressive Soccer Players - A Machine Learning Exercise

(Programming language: Python )

(joint work with Sanjay Pillay, Hao Wang and Wallun Chung)

(May - August 2020)

1. Visualization and Data Preprocessing

• Kaggle dataset (https://www.kaggle.com/stefanoleone992/fifa-20-complete-player-dataset) players_20.csv is used in this lab. The dataset provides detailed information of all the soccer players statistics in various clubs of major soccer leagues in the world. The data is originally from the FIFA soccer game created by EA sports. This game estimates the abilities of the actual players and built the game according to the data. And the Kaggle dataset is scraped from www.sofifa.com, where the gaming data is collected. The data we used is last updated on Sept 19th 2019.

• The dataset is important because the abilities of players is estimated from the actual players. FIFA is a very popular game and EA Sports is one of the largest sport video game developer. The player abilities estimate is quite accurate. Therefore, useful knowledge can be mined from the data for analyzing variety problems in the soccer industry. For example, wage analysis, player analysis, training strategy, budget analysis, sport gambling strategy plan can be performed using this dataset. Soccer has been a big industry which the market size is estimated to worth $488 billion in 2018 according to the Business Wire.

• Some of the analyses we are interested in to performs are:

• Run predictive model to predict wage from players abilities. We will select some features to run regression model. Also, we will try running PCA and regression model. To measure the effectiveness, we will use RMSE, MAE and R squared.

• Run classification model to classify players position from the players ability. To validate our model, we will use accuracy, precision, F1 score and ROC.

• We also intent to use the detailed game statistics from fbref.com. We can potential run analysis using the win/lose results from the real time data.

• Final report: https://hnguye01.github.io/DS7331/lab1_team_pms.html

2. Logistic Regression, Stochastic Gradient Descent and Support Vector Machine

• In this study, we will use different machine learning classification algorithms such as Logistic Regression (LR), Stochastic Gradient Descent Classifier (SGD) and Support Vector Machine (SVMs). We carry over the Business Understanding and Data Preparation from Lab 1 to this Minilab. More information related to Visualization and Data Preprocessing can be found in Lab 1 - Visualization and Data Processing.

• Final report: https://hnguye01.github.io/DS7331/minilab.html

3. Classification and Regression

• In this lab, we will use different machine learning algorithms for our two main tasks documented below.

Run predictive model to predict wage from players abilities (regression models). We will select some features to run regression models. Also, we will try running LDA and regression model. To measure the effectiveness, we will use RMSE, MAE and R squared.

Run classification model to classify players (classification models) position from the players ability. To validate our models, we will use accuracy, precision, F1 score and ROC.

• We carry over the Business Understanding and Data Preparation from Lab 1. More information related to Visualization and Data Preprocessing can be found in Lab 1 - Visualization and Data Processing.

• Final report: https://hnguye01.github.io/DS7331/lab2.html

4. Clustering Analysis

• In this lab, we will use different machine learning algorithms to implement clustering as a feature selection technique. We will compare a few of our existing models from Lab 2 to see if clustering provides any advantage on those models.

• For the the regression models that predicted player wages, we make an assumption that the super star players, average players, new players, or other types of players can make a big influence on the players' wage. Therefore, there maybe outliers that may affect the accuracy of the regression models. A superstar player usually get extremely high wages and we believe the key feature to identify those players are the attacking skill features. We will implement clustering to find the potential groups from the attacking features. Then, we will use the clustered result combining with rest of the features to run regression tests.

• We will be using MAE for the comparison. MAE measures the average magnitude of the errors in a set of predictions without considering their direction. It takes the average over the test sample of the absolute differences between prediction and actual observation where all individual differences have equal weight.

• Final report: https://hnguye01.github.io/DS7331/lab3.html

Bank Marketing Analysis

(Programming language: R )

(joint work with Dustin Bracy and Sabrina Purvis)

(April 2020)

• The retail banking industry provides financial services to families and individuals. Banks’ main functions are threefold; they issue credit in the forms of loans and credit lines, provide a secure location to deposit money, and allow a mechanism to manage finances in the form of checking and savings accounts. This analysis will focus specifically on the influential factors from direct marketing campaigns managed by a Portuguese banking institution in an attempt to get secure commitment for term deposits. Understanding not only which marketing campaigns were most effective, but also the timing of the campaign and the socioeconomic demographics will allow the retail banking industry to further target and tune their approach to securing term deposits.

• Bank Marketing data from this data set were used to address two project objectives:

1. Display the ability to perform EDA and perform a logistic regression analysis and provide interpretation of the regression coefficients including hypothesis testing, and confidence intervals.

2. With a simple logistic regression model as a baseline, implement additional competing models to improve on prediction performance metrics.

• Final report: https://hnguye01.github.io/DS6372/Stats2Pr2.pdf

Attrition Analysis

(Programming language: R)

(December 2019)

• DDSAnalytics is an analytics company that specializes in talent management solutions for Fortune 100 companies. Talent management is defined as the iterative process of developing and retaining employees. It may include workforce planning, employee training programs, identifying high-potential employees and reducing/preventing voluntary employee turnover (attrition). To gain a competitive edge over its competition, DDSAnalytics is planning to leverage data science for talent management. The executive leadership has identified predicting employee turnover as its first application of data science for talent management. Before the business green lights the project, they have tasked your data science team to conduct an analysis of existing employee data.

• Here I will do a data analysis on a given dataset CaseStudy2-data.csv to identify factors that lead to attrition. I will identify the top three factors that contribute to turnover (backed up by evidence provided by analysis). There may or may not be a need to create derived attributes/variables/features. The business is also interested in learning about any job role specific trends that may exist in the data set (e.g., “Data Scientists have the highest job satisfaction”). I also provide any other interesting trends and observations from the analysis. The analysis will be backed up by robust experimentation and appropriate visualization. Experiments and analysis are conducted in R. I will also build a model to predict attrition.

• Github Link: https://github.com/hnguye01/6306two

• Presentation slides: https://hnguye01.github.io/DS6306/html/Presentation.pdf

• Data Visualization App: https://hnguye01.shinyapps.io/DDSAnalyticsApp/

Beer Shiny Apps

(Programming language: R)

(November 2019)

• Using R Shiny to make my first app based on Budweiser - Case Study 1 (Project 1)

• Beer Shiny App link: https://hnguye01.shinyapps.io/beerapp/