Free RESume Checker
ATS Resume Checker
Create your resume and our real-time content analysis will automatically
check your resume content for best practices.
<script src="https://cdn.finsweet.com/files/add-to-cal/addToCalendar_5.js"></script><script></script>
// initialize the F'in sweet Cal Invite
var calendarInvite = fsCalendar({
// class of event title
title: '.event-title',
// class of event start date
start: '.event-start',
// class of event end date
end: '.event-end',
// class of event timezone
timezone: '.event-timezone',
// class of event Address
address: '.event-location',
// class of event Description
description: '.event-desc',
// multiple events on the page?
multipleEvents: true,
// class of the cms cal item
eventItemClass: '.event-item-content'
});
// initialize the F'in sweet Cal Invite
var calendarInvite = fsCalendar({
// class of event title
title: '.event-title',
// class of event start date
start: '.event-start',
// class of event end date
end: '.event-end',
// class of event timezone
timezone: '.event-timezone',
// class of event Address
address: '.event-location',
// class of event Description
description: '.event-desc',
// multiple events on the page?
multipleEvents: true,
// class of the cms cal item
eventItemClass: '.event-item-content'
});
Charles Bloomberg
• New York City, New York • charlesbloomberg@gmail.com • in/cbloomberg
SUMMARY
Experienced Data Scientist, passionate about leveraging Data to answer scientific and Business questions
EXPERIENCE
Data Scientist | Microsoft | New York, NY | June 2020 - Present
• Analyzed the company's sales data to identify the unmonetized Deal Registration transaction -and determine the total value of uncaptured opportunities.
• Built a Real-time opportunity evaluation engine to identify the best deals to be applied by a seller for every order to maximize the margins of the transaction. The outcome of the project estimated to generate additional revenue of 100 Million dollars over 3 years.
• Developed and deployed multiple propensity models by using machine learning methodologies indluding Random forest, XGBoost and SVM, to determine the propensity of a customer to buy a product category in the next 3 months, and applied the models to the existing customer base to generate leads for sellers and help the marketing team create personalized marketing campaigns.
• Built and deployed an NLP based model by fine-tuning BERT to determine the customers intent for tracking their shipment from customers to email, and provide an immediate and automated response of the current status of the customers' shipment with an SLA of less than 80 secs with a precision of 98%.
• Developed and deployed an information extraction tool to extract information from PDF's by using OCR to extract text and their relative positions from the PDF and build a transformer-based sequence model to extract the information with 92% accuracy.
• Built a Real-time opportunity evaluation engine to identify the best deals to be applied by a seller for every order to maximize the margins of the transaction. The outcome of the project estimated to generate additional revenue of 100 Million dollars over 3 years.
• Developed and deployed multiple propensity models by using machine learning methodologies indluding Random forest, XGBoost and SVM, to determine the propensity of a customer to buy a product category in the next 3 months, and applied the models to the existing customer base to generate leads for sellers and help the marketing team create personalized marketing campaigns.
• Built and deployed an NLP based model by fine-tuning BERT to determine the customers intent for tracking their shipment from customers to email, and provide an immediate and automated response of the current status of the customers' shipment with an SLA of less than 80 secs with a precision of 98%.
• Developed and deployed an information extraction tool to extract information from PDF's by using OCR to extract text and their relative positions from the PDF and build a transformer-based sequence model to extract the information with 92% accuracy.
Data Scientist Intern | Microsoft | New York, NY | June 2019 - June 2020
• Developed a Variational Autoencoder model, to create a reduced dimensional encoding of each cell in a single cell RNASeq data of the drug product generated by the different manufacturing process.
• Performed unsupervised clustering of the reduced dimension encoding to understand the percentage of T cell in the drug products generated by the different manufacturing process and performed statistical tests to answer why one process is better than the other.
• Developed a logistic regression model to determine the patient outcome from the reduced dimensional encoding of single-cell RNA seq data.
• Performed unsupervised clustering of the reduced dimension encoding to understand the percentage of T cell in the drug products generated by the different manufacturing process and performed statistical tests to answer why one process is better than the other.
• Developed a logistic regression model to determine the patient outcome from the reduced dimensional encoding of single-cell RNA seq data.
Lead Assistant Manager Data Sciences | Microsoft | New York, NY | June 2018 - June 2019
• Led the development of an AI-powered Content Extraction product by leveraging deep learning methodologies for a leading logistic company, to extract information from the invoices in a structured format with 87% accuracy. This product reduced the SLA for processing an invoice from 3 Mins an invoice to 20 secs.
• Developed a deployed an anomaly detection engine for a leading media client, to flag customer misuse of subscription. This solution leveraged real-time clickstream data by applying LSTM based deep learning models and generated an estimated $8.75 Million /year in savings to the client.
• Developed a deployed an anomaly detection engine for a leading media client, to flag customer misuse of subscription. This solution leveraged real-time clickstream data by applying LSTM based deep learning models and generated an estimated $8.75 Million /year in savings to the client.
EDUCATION
Master of Science in Biology - Data Science focus | New York University | 2020
SKILLS
Machine Learning: Python (scikit-learn, pandas, NumPy), keras, TensorFlow, Pytorch, Spark MLlib
Data Visualization Tools: Tableau, R Studio, Power BI, Latex, Advance Excel
Weak Bullet Points
2
Avoid using weak verbs to describe your experience. Replace "was, worked" with an action verb
Quantified Bullet Points
1
Add metrics to each bullet point when possible. Take a look at bullet 1.
Passive Voice
0
Avoid using passive voice when you describe experience. Try replacing built in this section.
The most talked about resume software of 2021
