Irene Bratsis

Intro

During my data science immersive apprenticeship program, I've learned about a number of classification and regression models, supervised and unsupervised learning algorithms and techniques, data cleaning, exploratory data analysis, data visualization techniques and storytelling tools I can bridge together to form a concise and relevant project that would be compelling for an audience of interest, client or leadership team.



Technical skills:

Python,
Statistics,
Numpy,
Pandas,
Probability,
Data Visualizations,
Data Exploration and Evaluation,
Sampling,
Storytelling with Data,
Distributions,
SQL,
Postgres,
Seaborn,
Matplotlib,
Data Cleaning,
Imputing Data,
Data Validation,
Experimental Design,
A/B, A/A testing,
Selection Bias,
Null Hypothesis Significance Testing,
Supervised & Unsupervised Learning,
Structured & Unstructured Data,
Feature Engineering,
Accuracy & Error Types,
Classification & Regression Algorithms,
NLP,
OLS,
KNN,
Random Forest,
Decision Trees,
Ensemble Modeling,
Support Vector Machines,
Boosting Models,
Clustering & K means,
Deep Learning,
Neural Networks,
Perceptron Models,
Supervised & Unsupervised Neural Networks,
Web Scraping & APIs,
Hadoop and Big Data Storage,
Spark,
BERT


Non-technical skills:
Empathy Global Strategic Account Management & Enterprise Sales,
Customer Success,
New Business Development,
Globalization Strategy Planning and Execution,
Negotiation,
Reporting & Budgeting,
Operations Management,
Marketing and Writing,
Servant leadership,
Intellectual curiosity,
Team building, collaboration and cultivating a positive environment!

Work

1. World Happiness Report Data has been used in this project to understand the dynamics and contributors to how we derive happiness. From jupyter notebook written in Python.
World Happiness Report: Capstone 1

2. Ether Pricing Data has been used in this project to understand the dynamics and contributors to predicting ether prices.
Ether Pricing Supervised Learning: Capstone 2
Presentation to go along with it can be found here

3. MovieLens Metadata Unsupervised Learning Capstone: In depth analysis with K means Clustering to discover structure in MovieLens metadata related to genres, movie titles, year and tags.
MovieLens Metadata Unsupervised Learning: Capstone 3
Presentation to go along with it can be found here

3. NLP Project:
NLP Project

4. Predicting Avocado Prices: Exporing the relationship between PLU, type, year and region on avocado prices with OLS
Predicting Avocado Prices: Capstone 4
Presentation to go along with it can be found here

5. Zillow and Economic Data Exploration: Final Capstone incorporating supervised and unsupervised learning techniques with federal economic data, state level median prices, price per square footage and days on the market, as well as city level median prices.
Final Capstone: Zillow and Economic Data Exploration
Presentation to go along with it can be found here

6. SQL Self Sufficiency Exam: Prompts completed as part of my SQL self sufficiency requirement.
Click here to see more.

About

I am a passionate Data Scientist and Machine Learning Engineer that's excited to share all my projects with the world! I loved the idea that I could better understand our reality through data and it's an absolute pleasure to be able to work on projects I find compelling enough to want to explore through data analysis, models, algorithms and fun data visualizations.

I am eager to find employment with a company that's looking to expand its data and machine learning applications. Having worked in the localization industry, I am particularly interested in NLP and NLG, but I am open to any data driven environment that provides an intellectual safe space to learn and experiment through data.

After a 10 year career in account management, customer success and sales, I was able to make a career transition into a dream field and I am looking forward to my next challenge.

Data science, machine learning, NLP, with strong soft skills background of 10+ years in account management and 6+ years in sales.

Technical skills:

Python,
Statistics,
Numpy,
Pandas,
Probability,
Data Visualizations,
Data Exploration and Evaluation,
Sampling,
Storytelling with Data,
Distributions,
SQL,
Postgres,
Seaborn,
Matplotlib,
Data Cleaning,
Imputing Data,
Data Validation,
Experimental Design,
A/B, A/A testing,
Selection Bias,
Null Hypothesis Significance Testing,
Supervised & Unsupervised Learning,
Structured & Unstructured Data,
Feature Engineering,
Accuracy & Error Types,
Classification & Regression Algorithms,
NLP,
OLS,
KNN,
Random Forest,
Decision Trees,
Ensemble Modeling,
Support Vector Machines,
Boosting Models,
Clustering & K means,
Deep Learning,
Neural Networks,
Perceptron Models,
Supervised & Unsupervised Neural Networks,
Web Scraping & APIs,
Hadoop and Big Data Storage,
Spark,
BERT


Non-technical skills:
Empathy Global Strategic Account Management & Enterprise Sales,
Customer Success,
New Business Development,
Globalization Strategy Planning and Execution,
Negotiation,
Reporting & Budgeting,
Operations Management,
Marketing and Writing,
Servant leadership,
Intellectual curiosity,
Team building, collaboration and cultivating a positive environment!

Contact

• fa-linkedin
• GitHub

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';