Saif Adeeb
Business & Data Science
Aspiring Data Scientist with 2+ years of analytical experience and currently working towards completing a part-time online Master's degree in Data Science. My goal is to transition into a role that allows me to apply my skills and knowledge in analytics and machine learning to solve challenging problems.
*************@*****.*** (408) 497 - 8007 San Mateo linkedin.com/in/saif-adeeb WORK EXPERIENCE
04/2018 – Present
Data Analyst
Samba TV
San Francisco, CA
Leveraged big data to derive insights and identify user behavior trends, gaps, and inconsistencies.
Produced reports to measure effectiveness of ad campaigns and communicated results to cross-functional teams.
Worked with Data Scientists to develop methodologies to create synthetic control groups for A/B Testing.
Experienced in writing and deploying production code. Tools: Python, Spark, SQL, Microsoft Excel, Git, PyCharm 05/2017 – 04/2018
Data Analyst
Cave Consulting Group
San Mateo, CA
Improved internal processes by creating scripts to automate data manipulation and other tasks.
Produced databases, tools, queries, and reports to analyze and summarize data to identify providers with the greatest savings potential. Built reports to identify savings for clients. Assisted in presenting savings reports to upper management and operations team to improve strategies and operations.
Experienced with manipulating, cleaning, and analyzing data. Tools: Python, SQL, Microsoft Excel, Qlikview
08/2016 – 05/2017
Item Setup Specialist
Walmart eCommerce
San Bruno, CA
Set up items across many different departments by creating items in eCommerce databases through QMF, PIM, and Retail Link. Ran weekly reports to analyze data's validity across different databases using SQL and Microsoft Excel.
Analyzed and interpreted data to identify costs, common issues, and team's efficiency for each department.
Tools: SQL, Microsoft Excel
01/2016 – 06/2016
Undergraduate Research Assistant
University of California, Davis
Davis, CA
Forecasted weather using solar irradiance data from the Pacific Northwest using time series analysis.
Created functions for weather forecasting. Created directional plots to visualize data using ggplot.
Presented findings at a UC Davis Statistics Conference. Tools: R
PROJECTS
Predicting House Prices in Ames, Iowa (08/2018 – 09/2018) Goal: Build a model to predict the sale prices of residential homes in Ames, Iowa based on features of the homes.
Used correlation plots and visualizations to examine relationships among different features and homes' sales prices.
Trained and tuned Ridge, Lasso, Elastic net, XGBoost, and Ensemble regression models to find the best performing model. Compared the models' prediction accuracy and found that the Ensemble model achieved the best results.
Tools: Python
What's Cooking? - Recipe Cuisine Prediction
(06/2018 – 08/2018)
Goal: Build a classification model to categorize recipes into cuisines based on the ingredients.
Used TF-IDF to extract and generalize features from list of ingredients. Trained and tuned Random Forest, Logistic Regression, and Support Vector Machine models to find the best performing classification model. Compared the models' categorization accuracy and classification reports and found that the Support Vector Machine model yielded the best categorizing results.
Tools: Python
MNIST - Digit Recognizer (05/2018 – 06/2018)
Goal: Build a classification model to classify handwritten digits from the MNIST dataset.
Used convolutional neural networks and artificial neural network to build classification models. Designed an experimental design to examine the effect of classification accuracy by altering nodes and layers for artificial neural networks and max pooling layers and kernel sizes for convolutional neural networks.
The experimental design showed that convolutional neural networks yielded the best results.
Tools: Python, TensorFlow
Decision Rules for Harvesting Abalones
(10/2017 – 12/2017)
Goal: Conduct an alternative approach to a previously unsuccessful study on predicting the age of abalones.
Hypothesized reasonings for the unsuccessful study and used findings from the exploratory data analysis to support conclusions. Compared models using false positive and false negative rates to identify the model that yielded the lowest error rates. Tools: R
EDUCATION
06/2017 – Present
M.S. in Data Science
Northwestern University
Expected Graduation: Spring 2019
09/2014 – 06/2016
B.S. Managerial Economics, Statistics minor
University of California, Davis
SKILLS
Python R SQL Spark Machine Learning
QlikView Tableau Microsoft Office Suite
Tasks/Achievements
Tasks/Achievements
Tasks/Achievements
Tasks/Achievements