Designed and implemented a scalable real-time analytics pipeline using Apache Kafka, Spark Structured Streaming, and MongoDB to simulate NYC MTA turnstile data and forecast real-time subway foot traffic using SparkML Random Forest models.
python bash machine-learning big-data apache-spark mongodb random-forest sparkml prediction pyspark apache-kafka data-pipeline streaming-data structured-streaming spark-sql real-time-streaming time-series-forecasting foot-traffic nyc-mta
-
Updated
May 5, 2025 - Jupyter Notebook