Data Scientist | Graduate Student at UT Austin
Based in Seattle, WA
I work on projects which turn data into insights and insights into high-value products or business solutions.
• Keep it Neutral: Using Natural Language Inference to Improve Generation. • Mitigating Dataset Artifacts in Natural Language Inference Through Automatic Contextual Data Augmentation and Learning Optimization. • CLFD: A Novel Vectorization Technique and Its Application in Fake News Detection.
Sales Recommender System: A machine learning application for monthly sales optimization in order to schedule sales visits efficiently. When used in industry, it increased the conversion rate by 9% and the respective revenue by 11% over a year. Online Price Aggregator: A web scraping...
Natural Language Processing (NLP) Portfolio
Linear Sentiment Classification, Sentiment Classification with Feedforward Neural Networks, Hidden Markov Models and Conditional Random Fields for Named Entity Recognition, Character Language Modelling with Recurrent Neural Networks, Character Language Modelling with Temporal...
Computer Vision (CV) Portfolio
Image Classification with Feedforward Neural Networks, Image Classification with Convolutional Neural Networks, Semantic Segmentation with Fully Convolutional Neural Networks, Point-Based Object Detection with Fully Convolutional Neural Networks and Generalized Focal Loss, Vision-Based...
2022 - 2023
Graduate Research Assistant at UT Austin NLP Lab
• Developed an effective method for ChatGPT models (GTP‑3.5 and GPT‑4) to detect and correct their own errors, by combining two differently prompted instances of the model in order to emulate the human cognitive process associated with reasoning. • Improved the performance of AI text generation models (GPT-3 and GPT-J) by incorporating natural language inference in order to dynamically adjust the decoding strategy parameters and perform controlled text generation. • Increased the effectiveness of AI natural language inference models (BERT, BART and ELECTRA) by proposing a novel method of data augmentation, combined with contrastive learning and a hybrid loss function.
2019 - 2021
Data Scientist at Pharmasept SA
• Conceptualized and developed a recommendation algorithm, based on machine learning and time-series forecasting, to automatically schedule the daily route of each sales consultant to their extensive network of customers, as a result minimizing the risk of failed sales visits and increasing annual revenue generation by 11%. • Designed the budget forecast for the sales department using predictive analytics, resulting in a sales target for each product. • Utilized statistical techniques, such as a weighted ABC analysis and K-means clustering, for product and customer segmentation. • Communicated findings and visualizations to advise the stakeholders on strategic decisions for the company.
2021 - 2023
MS in Computer Science, The University of Texas at Austin
GPA: 4.00 - Major: Computer Science, Minor: Data Science and Business Analytics
2013 - 2019
BEng and MEng in Electrical and Computer Engineering,Technical University of Crete
Class Rank: 7th