Mick is available for hire
Hire MickMick Nassar
Verified Expert in Engineering
Data Analysis Developer
Los Angeles, CA, United States
Toptal member since June 24, 2020
Bio
Mick is a seasoned developer with experience at a Fortune 100 company creating real-time enterprise API solutions, machine learning implementations in multiple languages, and products worth millions of dollars with several patents pending. He loves what he does, and he's good at it. Let him put his skills to work for you.
Portfolio
Cigna
Python, PySpark, Spark NLP, Apache Hive, Bash Script, Perl, NumPy, Pandas...
Express Scripts
Zeppelin, Hadoop, Java, Scala, Apache Spark, Oracle, Machine Learning, HBase...
Express Scripts
Oracle, Pega, Java, Agile, Confluence, Eclipse IDE, OAuth, Grafana, REST APIs...
Experience
Availability
Part-time
Preferred Environment
Zeppelin, Hadoop, Python, Scala, Spark, MacOS
The most amazing...
...project I've created so far is called Adverse Events. It reads millions of rows of call data using NLP technology to identify when a patient reports an ADE!
Work Experience
Machine Learning Engineer
2019 - PRESENT
Cigna
- Designed a Spark K-Means classifier running on Spark NLP embeddings generated from free text transcripts of phone calls to identify words indicative of an Adverse Event. This product will improve patient safety and expand an existing revenue stream.
- Applied PCA dimensionality reduction on NLP embeddings to visualize clusters generated and easily identify areas of focus without having to label data. This approach saved much time and manual work, enabling the use case to move expeditiously.
- Launched our pilot product and received an enthusiastic response. Out of about 2 million rows of transcript data, the solution returned about 5,000 words for review. In the first 19 calls reviewed a reportable AE was identified.
Technologies: Python, PySpark, Spark NLP, Apache Hive, Bash Script, Perl, NumPy, Pandas, Scikit-learn, Zeppelin, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Agile, Linux, SQL, Data Analysis, Data Modeling, Machine Learning, PyCharm
Machine Learning Engineer
2018 - 2019
Express Scripts
- Crafted a binary KNN classifier in Scala with Hamming distance from a training set I translated into binary code. This improved processing time so the model could be used with a streaming solution and externalized spring API in real-time.
- Encountered a challenge at the end of the pilot as we discovered the current claim process didn't make enough features available when predictions needed to be invoked. We collaborated with the business, outlining the challenges and possible solutions.
- Wrote scripts for auto restarting APIs, auto fetching logs from distributed databases, monitoring dashboards with Splunk enterprise and more as needed. This laser precise solution will yield the company an estimated $29 million in savings every year.
Technologies: Zeppelin, Hadoop, Java, Scala, Apache Spark, Oracle, Machine Learning, HBase, Spark Streaming, Agile, Linux, SQL, Phoenix, Apache Kafka, Data Analysis, Bash Script, Data Modeling, REST APIs, RESTful Development, IntelliJ IDEA
Associate Software Engineer
2017 - 2018
Express Scripts
- Created an enterprise API in Java around a legacy product called Oracle Advanced Queue. It facilitates enterprise wide patient eligibility searches, saving about $100,000 dollars every year. It was the biggest value added FY 2017 on the project.
- Built new Pega applications that automate and manage the lifecycle of a specialty prescription, including a payer selection system that maps an individual’s insurance information to corresponding claim centers with 95% accuracy.
- Solved a difficult problem that arose in an MVP1 production release that was impeding our entire project because users were unable to process payer information. I received recognition from my organization’s VP afterward.
- Authored many confluence pages to help our engineers, users, and business stakeholders understand our software. I also worked with the end user experience team to address technological barriers to innovation and improve productivity.
Technologies: Oracle, Pega, Java, Agile, Confluence, Eclipse IDE, OAuth, Grafana, REST APIs, RESTful Development, SQL, PegaRULEs Process Commander (PRPC)
Experience
Adverse Events (AE)
After becoming a part of Cigna, I collaborated with my team to launch a new project called Adverse Events that I successfully pitched to management. I designed a Spark K-Means classifier running on Spark NLP embeddings generated from unlabeled free text transcripts of patient phone calls to identify words indicative of an Adverse Event. This product will improve patient safety, aid the company in meeting contractual obligations and significantly expand an existing revenue stream.
Incorrect Claim Center (ICC)
Using a KNN classifier handwritten in Scala using Hamming distance, I created a solution to determine the benefit type to bill on a prescription from a historical train set. Manually performing this billing nuance incorrectly costs the company $30 million every year.
Enterprise Eligibility API
I created an enterprise API written in Java around a legacy product called Oracle Advanced Queue. It facilitates enterprise-wide patient eligibility searches to ensure that a patient has active insurance before dispensing specialty prescriptions.
Education
2018 - 2019
Courses in Mathematics
Harvard Extension School - Cambridge, MA, USA
Certifications
DECEMBER 2018 - PRESENT
Data Science with Python
Accelebrate
NOVEMBER 2017 - PRESENT
Certified System Architect
Pegasystems
JANUARY 2017 - PRESENT
Computer Science 101
LaunchCode
Skills
Libraries/APIs
PySpark, REST APIs, Pandas, Spark Streaming, Scikit-learn, NumPy, Spark NLP
Tools
PegaRULEs Process Commander (PRPC), Splunk, Confluence, Eclipse IDE, Grafana, IntelliJ IDEA, PyCharm
Languages
Scala, SQL, Bash Script, Java, Python, JavaScript, Perl
Frameworks
Apache Spark, Hadoop, Phoenix
Paradigms
RESTful Development, Agile
Platforms
Zeppelin, Apache Kafka, MacOS, Linux, Pega, Oracle
Storage
HBase, Apache Hive
Other
Machine Learning, Data Analysis, Natural Language Processing (NLP), Progressive Web Applications (PWAs), Generative Pre-trained Transformers (GPT), Data Modeling, OAuth
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring