Projects
Some of the cool projects and applications I have worked on!
IMDb Data Analysis with Spark
Distributed Spark pipeline for extracting insights from 41M+ IMDb records, with a head-to-head benchmark of Scala RDD vs PySpark SQL APIs.
PythonPySparkScalaApache SparkDocker
Financial Market Prediction with LLMs
Multimodal financial market prediction pipeline combining ETF stock data with LLM-extracted sentiment.
PythonPyTorchOptunaPandas