Ezan Kodjo Email & Phone Number

Remote

During my time with Verizon I was tasked with monitoring, repairing, and reviving, ongoing use cases where I :Juggled multiple use cases at once with various demands and different product owners .Wrote scripts in Python that automated text summation and classificationRestructure and improved preprocessing across multiple use cases Interpreted wants and needs of product owners to allow for smoother execution by engineersOrganized and collaborated with engineers to to bring my created itinerary to fruitionPrepared data for collaboration with machine learning models.Increased the understanding of product owners and leadership alike regarding quirks and obstructions of established, active models Improved the classification performance of a use case by upwards of 100%Architected, built, maintained, and improved new and existing suite of algorithms and their underlying systems.Analyzed large data sets apply machine learning techniques and develop predictive models, statistical models and developing and enhancing statistical models by leveraging best-in-class modeling techniques Implemented end-to-end solutions for batch and real-time algorithms along with requisite tooling around monitoring, logging, automated testing, performance testing and A/B testing.Worked closely with engineers to verify performance of existing models in order to allow for use to fulfill U.S. government needs Established scalable, efficient, automated processes for data analyses, model development, validation and implementation.Implemented Model Drift Monitoring and Retraining Strategies.

Atlanta, Georgia, United States /Remote

A consulting firm where my position of Senior Data Scientist had me Built a personalized in-session product recommendation engine.Next-Best offer prediction.Anomaly detection and Root Cause Analysis.Unified consumer profile with probabilistic record linkage.Visual search for similar and complementary products.Implemented end-to-end solutions for batch and real-time algorithms along with requisite tooling around monitoring, logging, automated testing, performance testing and A/B testing.Worked closely with data scientists and analysts to create and deploy new product features on the ecommerce website, in-store portals and mobile apps.Architected deployment solutions using AWSImplemented Model Drift Monitoring and Retraining Strategies.Sagemaker Model transformation into dedicated preprocessing, inference and model validation scripting.Used Python, NLTK, Tensorflow to tokenize and pad comments/tweets and vectorize sentiments. Vectorized the documents using Bag of Words, TF-IDF, Word2Vec, GloVe to test the performance it had on each model. Created and trained an Artificial Neural Network with TensorFlow on the tokenized documents/articles/SQL/user inputs. Performed Nearest Entity Recognition (NER) by utilizing ANNs, RNNs, LSTMs, and Transformers. Involved in model deployment using Flask with a REST API deployed on internal Bank of America systems. Built a deep learning model for text classification and analysis. Performed classification on text data using NLP fundamental concepts including tokenization, stemming, lemmatization, and padding. Performed EDA using Pandas library in Python to inspect and clean the data. Visualized the data using matplotlib and seaborn. Explored using word embedding techniques such as Word2Vec, GloVe, and Bert.

Consulting firm that had me work on various internal projects to further enhance the company. The following points are a broad stroke on the experience but further elaboration can be found in the portfolio attached.Use of technologies/Environments include Java, JavaScript, TypeScript, CSS, HTML, PostgreSQL, React, Node.js, Express, AJAX, Crypto-js, BCrypt, Enzyme, Python, and R

Glassboro, New Jersey, United States

The Preparation for Industrial Careers in Mathematical Sciences program is a Mathematical Association of America program sponsored by the National Science Foundation (NSF) and the National Security Agency (NSA) engineered to prepare its participants for a career in industry. The company my group (3) had done computer vision for TransDAC LLC: Intelligent Transportation Systems, which had me:Create, filter, and augment training dataImage feature extractionSpearheaded communications with the product owner in order to tackle challenges as well as define metrics for success Utilized a multi layer perceptron to achieve an accuracy of 96% in our classification of “good” vs “bad” roads Write a scientific paper detailing the team’s computer vision endeavors in LaTexPresented findings to product ownerThe code was ensured to be small enough to be able to run on a Raspberry Pi in order to be easily distributed amongst all of their vehicles.

Interactive Analytics is a software development firm. Established the NLP (Natural Language Processing) Lab at II to research ways to better interact with users in written form. Used TF-IDF and NLTK techniques to classify, segment and analyze sentiment of textual data. Implemented various text analysis projects and built-in house NIP libraries in Python to clean, preprocess and tokenize incoming textual data. Implemented application of various machine learning algorithms and statistical modeling like Decision Trees, Text Analytics, Sentiment Analysis, Naive Bayes, Logistic Regression and Linear Regression using Python. and determined performance. Interrogate analytical results to resolve algorithmic success, robustness and validity. Implemented Agile Methodology for building an internal application. Wrote a Flask app to call CoreNLP for parts-of-speech and named entity recognition on natural English queries. . Analyzed large data sets, applied machine learning techniques and developed predictive models, statistical models and developed and enhanced statistical models by leveraging best-in-class modeling techniques. Design, develop and produce reports that connect quantitative data to insights that drive and change business.