GEOVANI A. MONTOYA
909-***-**** adcmrn@r.postjobfree.com
MEDIA
LinkedIn: geovani-montoya
Github: geovani-montoya
Kaggle: geokywankenobi
Portfolio: geovani-montoya.github.io
EDUCATION
DEC 2021
MS in Computational Finance &
Risk Management
UNIVERSITY OF WASHINGTON, SEATTLE
DEC 2019 JUL 2020
MS in Physics MS in Chemistry
CALIFORNIA STATE UNIVERSITY, LA
SEPT 2017-DEC 2018
Non-Degree in Applied and
Computational Mathematics
CALIFORNIA INSTITUTE OF TECHNOLOGY
JUN 2013
BS in Chemistry (ACS certification)
UNIVERSITY OF CALIFORNIA, IRVINE
PROFESSIONAL DEVELOPMENT
JAN 2019-APR 2020
Nanodegrees in Data Scientist,
Artificial Intelligence for Trading,
Natural Language Processing,
Data Engineer
UDACITY
DEC 2019-APR 2020
Big Data and Data Science Master
INTELLIPAAT
PROFESSIONAL AREAS
§ Machine Learning
§ Data Engineering and Big Data
§ Data Visualization
§ Statistics and Probability
§ Natural Language Processing
§ Time-Series
§ Credit Risk Analysis
§ Customer Service Analytics
TECHNICAL SKILLS
§ Python, R, SQL, BASH
§ Hadoop, Kafka, Hive, Cassandra,
HBase, Redshift, Airflow
§ Tensorflow, Keras, PyTorch,
Spark, Scikit-learn
§ Tableau, Power BI
§ AWS
DATA SCIENCE PROJECTS
Artificial Intelligence for Quantitative Research OCT-DEC 2019
§ Developed NLP models to text mine corporate filings, such as 10Q and 10k statements, using bag-of-words and TF-IDF to generate company-specific sentiments and signal optimal times to buy/sell their stock.
§ Built deep neural networks to process and interpret news data by constructing and training LSTM networks for sentiment classification.
§ Developed deep learning models to generate trading signals using RNN and LSTM algorithms and evaluated results via backtesting. Customer Segmentation APR-MAY 2019
§ Built and optimized machine learning models (PCA and K-means) to predict target customers for mail-in advertisements using Scikit-learn libraries in Python.
§ Developed data pipeline for the data wrangling and feature engineering process to optimize machine learning models real-time. L.A.’s Homeless Population Predictions with Data Kind JUL 2018
§ Developed advanced statistical models, such as survival analysis, that captured the missing dynamics in previous models, used by legislation, to estimate annualized population experiencing homelessness; published in Los Angeles Times and Economic Roundtable.
EXPERIENCE
Financial Services Professional New York Life APR 2019-PRESENT
§ Top performer for three consecutive months based on increasing revenue by
$40,000.
§ Created/optimized investment and insurance portfolios for clients.
§ Designed/implemented marketing plans, including outreach programs and community events, resulting in an increase of monthly sales by 25%. Research Fellow CSULA JUL 2013–NOV 2018
Visiting Researcher Comp. Env. Science Lab at UC Irvine JUN-AUG 2014
§ Developed many-body theoretical models for semi-conductors with code (for numerical analysis) accurately predicting experiments.
§ Served as liaison/lead scientist between 3 collaborating teams.
§ Built data pipeline to automated data analysis via scripting in Python, increasing speed of analysis from 12 hrs/dataset to less than 5 min/dataset
(total of 500+ datasets).
Research Intern UC San Diego JUN-AUG 2015
§ Used high-performance computing to run molecular dynamic simulations via object-orient programming in Fortran and Python and calculated probability distributions of chemicals from simulation data.
§ Developed a pipeline in BASH to clean and manage large data sets. Data Analyst Researcher Atmospheric Integrated Research Institute at UC Irvine JAN 2012-JUN 2013
§ Automated data analysis and performed QQ tests using MATLAB to identify an quantify molecular concentrations of air particles.
§ Used linear regression to quantify concentrations and develop metrics used to report on grants and future publications.
ACTIVITIES
Dean of Pasadena Chapter School of Artificial Intel. AUG 2018-NOV 2019 Active Competitor (highest rank was top-6%) Kaggle