Programming Languages: Java, Python, R, JavaScript, PHP, SQL, C#
Tools/Software: PowerBI, Tableau, GIT, Hadoop, Spark, Microsoft Power Platform, Django, Flask
Data Science: NLP, time series, Deep Learning(LSTM,RNN,CNN,GAN), Machine Learning (NumPy, scikit-learn, pandas, Keras, TensorFlow, PyTorch), Recommendation Systems
Soft Skills: Teamwork, Creativity
Proficient
Pre-intermediate
Prompt engineering to extract fund and sub-fund names from the prospectus.
Generalize a script using table extraction and Openai API to generate an output in a specific format using a prospectus as an input document.
ESG Project - Analytix:
Collect ESG information from alternative data sources.
Extract ESG goals from sustainability reports over 5 year period of 200 big companies.
Build a pipeline of text extraction and ESG goal detection from CSR reports for the ESG Goal Tracker project.
TS-Expert project:
Automatically extract information from term sheets using OCR techniques.
Create a NER model with Spacy for keyword extraction from financial documents.
Table detection and extraction from financial records (IRS, FX, CRS...).
Technologies: Python, PaddleOCR, Selenium, OpenAI API, Data Analysis
Develop an End-to-End Machine Learning Toolkit following the CRISP methodology.
Technologies: Python, Plotly, FeatureTools, Optuna, Ray.Tune, Pipelines, Scikit-Learn, Flask