Improver

Contact Details

E-mails & Phone

Marcelo Mendonca

Marcelo Mendonca

Data Analytics | AI | Data Science | ML | Innovation

Austin, Texas Metropolitan Area

Experienced data analytics/data science professional with 23+ years of extensive international experience obtained from several positions within Australia/Asia, South America and North America.

I engage with a variety of business stakeholders to understand the problem and translate it into practical data analytics solutions that drive action and real business outcome. Curious business mentality and meticulous attention to detail are crucial in this phase.

Next, comes the data. I would love to apply state-of-the-art machine learning models with nice and clean datasets. However, data is not always readily available, and in most cases, it is messy. I specialize in finding, collecting, cleaning, and transforming datasets.

After completing exploratory data analysis, building and validating machine learning models, it’s time to communicate the results. I have expertise in building intuitive data visualizations, dashboards and reports that tells a story and provides actionable insights. I communicate complex analysis and concepts to a variety of audiences, in a clear and concise manner.

Selected projects:
+ Anomaly Detection with LSTM Autoencoder: Complex manufacturing conveyor system with 70+ time series.
+ NLP - SEC Fillings Sentiment Analysis: Web-scraped and parsed 10-K fillings from EDGAR database. Developed WebApp for data annotation. Used Fastai library to fine-tune sentiment classification model.
+ NLP - Udemy Course Review: Web-scrapped 30,000+ reviews. Used HuggingFace Transformers library to fine-tuned a multi-class (DistilBERT) model for intent classification.
+ Australian Housing Market: Web-scrapped data from 4+ million properties and applied advanced analytics to understand key factors driving price growth.
+ Data Analytics Training: Trained 6,000+ professionals in 4 continents and 12 countries.

Specialties:
+ Recruiting, developing and leading teams of data analysts
+ Strong Python programming, Jupyter Notebooks, Git
+ Relational Database, SQL, ETL
+ Familiarity with Big Data tools including PySpark, Hadoop, Hive, Hue
+ Advanced Analytics and Exploratory Data Analysis
+ ML/scientific packages (e.g. pandas, numpy, scikit-learn, keras)
+ NLP and pre-trained models (e.g. Transformers, spaCy, BERT, GPT-2)
+ Machine learning/deep learning models for classification, regression, clustering, and anomaly detection
+ Data visualizations and dashboards (e.g Power BI, Plotly, Matplotlib)
+ Advanced MS Excel including automation with VBA
+ Web-scrapping (BeautifulSoup, Selenium)
+ Web Applications (REST APIs, Flask, Django, GraphQL, React, NextJS)


Experience:

  • Data Scientist - Industry 4.0 (General Motors)
  • Software Engineering Manager (GM Holden)
  • Facilities and Body Shop Maintenance – Electronics Technician (General Motors)
  • Software Engineer (General Motors)
  • Senior Software Engineer (GM Holden)

Skills:

People also viewed these profiles

People also viewed these profiles

Magdalena Wisniowska

Senior Program Manager, TA Learning&Development at Amazon Web Services (AWS) @ Berlin, Berlin

People also viewed these profiles

Adam W.

Principal Database Engineer/Architect at Covetrus @ Atlanta Metropolitan Area