e# Kyle Pelham - Data Analytics Portfolio

About Me

Hi there! My name is Kyle Pelham, and I’m a recent graduate of Master of Science, Business Analytics program at California Polytechnic State University, San Luis Obispo.

Before to grad school, I was a Marketing and Commerce Consultant at Deloitte Consulting LLP where I built out requirements and supported the implementation of Customer Data Platforms and Marketing Automation tools.

One of my strengths is my ability to communicate technical information to non-technical stakeholders in a clear and concise manner. I understand the importance of data-driven decision-making and have worked with teams across various industries to help them make informed choices.

In this portfolio, you’ll find examples of data analytics projects I’ve worked on. Each project showcases my ability to analyze data, develop insights, and present my findings in a compelling way.

Please contact me if you have any questions!

• kyleplhm@gmail.com
• Linked In

Data Analytics Projects:

1. Proactive Constraint Flow Management: Real-time Detection and Analysis for Enhanced Power Grid Stability

• Individual contribution to a collaborative Cal Poly MSBA capstone project, partnering with a prominent North American utilities company.
• Employs the “onlineBcp” R package for real-time detection of significant shifts in power output time series data using Bayesian probabilities.
• Utilizes anonymized historical data for a single constraint, illustrating constraints as power grid limitations influenced by factors such as transmission capacity, generation limits, network topology, and regulations; constraint flow represents the electricity flow within these constrained segments.
• Identifying substantial changes in constraint flow enables utilities companies to proactively maintain grid stability during regime changes by alerting them in advance.

2. Chipotle Customer Segmentation: A K-means Clustering Approach to Survey Analysis

• Survey data cleanup: Conduct general preprocessing of survey responses to ensure data quality.
• Dimensionality reduction: Use Sci-kit Learn’s PCA (Principal Component Analysis) to reduce survey dimensions while preserving important information.
• K-means clustering: Perform k-means clustering on the transformed data using Sci-kit Learn to identify distinct customer segments.
• Cluster labeling: Apply the cluster labels to the original data for further comparative analysis.
• Exploratory Data Analysis (EDA): Investigate each cluster’s unique characteristics and differences to better understand customer preferences and behaviors.
• Marketing strategy suggestions: Leverage insights from the cluster analysis to propose tailored marketing strategies for each customer segment.tilizes Sci-kit Learn package to reduce survey dimensions with Principle Component Analysis and perform k-means clustering on the transformed data.

3. Exploring the Relationship Between World Happiness and the Big Mac Index

• Consolidating and processing seven years of Big Mac Index and World Happiness data into a unified dataframe for analysis.
• Conducting an exploratory data analysis to examine the potential correlation between the Big Mac Index and World Happiness scores.
• Utilizing Pearson’s correlation coefficient to quantitatively assess the relationship between the two indices.

4. SLO Pop-Up Ordering System: Database Design and Implementation

• Eliciting requirements and establishing business rules for the development of a relational database using MySQL, tailored for a pop-up ordering system.
• Creating an advanced Entity-Relationship (ER) diagram to ensure a comprehensive database structure and verifying the normalization of tables for optimal performance.
• Developing a functional prototype, including a database creation script, to facilitate rapid deployment and testing of the system.
• Effectively demonstrating the ordering workflow through a series of well-structured SQL queries and the utilization of dummy data, showcasing the system’s capabilities and potential for real-world applications.

Cal Poly MSBA Courses Taken

• GSB 518. Essential Statistics for Business Analytics: Statistics background needed for analysis of business data and econometrics. Topics include basics of probability theory, random variables, distribution functions, conditional distributions, independence, expectations, covariance, correlation, random samples, estimation, asymptotic theory, hypothesis testing, and confidence intervals.

• GSB 520. Data Management for Business Analytics: Exploration of data management including relational databases, data warehouses, and NOSQL databases. Foundation for analyzing, designing, implementing and using information repositories in a business environment. Topics include the database development life cycle, data modeling, SQL programming, data quality and integration.

• GSB 530. Data Analytics and Mining for Business: Exploration of the concepts, tools and techniques of data mining in the business context, using case study and problem-solving approaches. Topics include multidimensional data modeling, predictive analytics, pattern discovery, forecasting, text mining, and data visualization.

• GSB 544. Computing and Machine Learning for Business Analytics: Use of computers for advanced data analysis in business analytics. Topics include computer programming using statistical software, data gathering and cleaning, and machine learning.

• GSE 519. Econometrics and Data Analysis: Identification and estimation of linear and nonlinear regression models for analyzing business data. Topics include multiple linear regression; model selection; robust standard errors; instrumental variables; maximum likelihood estimation; logit/probit, ordered logit/probit, and other microeconometric models.

• GSB 516. Strategic Marketing Analytics: Analysis of customer information, using a broad range of tools and techniques including predictive, statistical, and optimization models. Integration of data into reporting platforms. Application of findings to marketing decision-making.

• GSB 545. Advanced Machine Learning for Business Analytics: Use of computers for advanced machine learning in business analytics. Topics include boosting, ensemble learning, Bayesian methods, and various types of neural networks.

• GSB 521. Cloud Services & Applications for Business Analytics: Apply cloud resources for business analytics. Identify business benefits of cloud computing, storage, networking, data management and security. Use web services to analyze big data including query, statistical analysis, machine learning and visualization.

• GSB 570. Financial Time-Series: Analysis of time-series to evaluate the risk and return of the main products of capital markets.