Real-time Sentiment Analysis on Cryptocurrency Market Trends
Real-time ingestion + NLP scoring with dashboards for insights.
AWSNLPBERTStreaming
Karan Ajay Pisay
Turning data into actionable insights — building reliable pipelines, productionizing ML, and enabling business decisions with high-quality, governed data.
Spark / PySpark
Airflow
Snowflake
AWS
dbt
Great Expectations
About
Background • Focus areas • What I build
A dedicated and results-driven Data Professional with a proven track record in transforming data into strategic insights.
With expertise in SQL, Python, and
machine learning, I have reduced costs, optimized processes, and enhanced decision-making in
dynamic environments. My experience spans automating data pipelines to developing
predictive models, always aiming to deliver practical, measurable impact.
Welcome to my portfolio — where data meets actionable intelligence.
Projects
Hover a card for details
Data Pipeline for E-commerce Analytics
Low-latency pipeline + dashboards to improve decisions and ops.
KinesisRedshiftGlueTableau
Automotive Customer Insights and Sales Forecasting
Customer analytics + time-series forecasting for strategic planning.
SnowflakeScikit-LearnProphetEDA
News Shack Live News Summarizer
Fine-tuned transformer summarization with a simple UI.
TransformersT5StreamlitNLP
Sentiment Analysis on Russia-Ukraine Invasion
Social/news sentiment modeling using VADER + BERT.
VADERBERTAWSStreamlit
Fraud Detection in Financial Data
Fraud classification using ML + tuning for generalization.
MLRandom ForestLogRegPySpark
CyberBullying Detector using NLP
Tweet classifier with SVM + real-time predictions UI.
SVMTF-IDFStreamlitNLP
Spotify Charts Analysis
Big data analysis in Databricks to uncover streaming trends.
DatabricksPySparkBig DataAnalytics
EDA on CDC STDs Dataset
Exploratory analysis to identify trends and distributions.
PandasMatplotlibEDATime Series
Customer Churn Prediction
Behavior-based churn model to enable proactive retention.
SageMakerXGBoostSQLTableau
Articles
Selected papers & writing
Experience
Roles & impact
Data Engineer — Webull Technologies, Inc. (Florida, USA)
December 2024 – Present
- Designed and optimized ETL/ELT pipelines using Apache Spark (PySpark) and Apache Airflow to integrate large-scale marketing, trading, and behavioral datasets, improving processing speed and reliability by 70%.
- Built scalable data pipelines on Snowflake and AWS for automated ingestion, transformation, and storage, ensuring consistency, performance, and compliance with data-governance standards.
- Partnered with Data Science teams to productionize ML models in AWS SageMaker (churn prediction, credit-response modeling) and integrated outputs into analytical dashboards for actionable insights.
- Implemented data-quality frameworks using SQL, PySpark, and Great Expectations, improving accuracy and monitoring across data pipelines and analytical layers.
- Collaborated with Product, Marketing, and Risk teams to standardize data lineage, CI/CD deployment, and dbt-based transformation workflows, enhancing transparency and maintainability.
Enterprise Applications Data Analyst — Tri-County Electric Cooperative Inc. (Texas, USA)
September 2023 – December 2024
- Automated data extraction with SQL and Alteryx using Tableau for forecasting, reducing electricity procurement costs by 60%.
- Developed high-accuracy ML models for forecasting power consumption using real-time data, cutting resource wastage by 15%.
- Enhanced financial efficiency by 30% through ad-hoc analysis using Python and process optimization resulting in enterprise cost savings.
- Improved resource reliability by geospatially plotting high consumption areas and implementing fault-tolerant measures.
Marketing Data Analyst — LeveragAI (California, USA)
June 2023 – September 2023
- Leveraged predictive models to enhance targeting precision and analyze customer behavior, increasing campaign engagement by 25%.
- Implemented reporting using AWS QuickSight and pivots in Excel to deliver KPI dashboards and financial reports for decision-making.
- Led CRM integration and adoption of marketing tools, automating processes and achieving 12% revenue growth in one quarter.
Data Engineer — Triangular Automation Pvt Ltd (India)
July 2018 – June 2021
- Engineered robust ETL pipelines with PySpark and SQL to process credit data, enhancing integration and data quality by 40%.
- Created and maintained machine learning models for customer segmentation, improving credit risk assessments.
- Built scalable architectures on AWS (S3, Redshift, Glue) optimizing storage and retrieval for near real-time evaluations.
- Developed ARR/MRR and inbound lead conversion dashboards; performed feature engineering to optimize the sales funnel and inform targeting decisions.
Education
Degrees & coursework
Master of Professional Studies in Data Science — UMBC (Baltimore, MD)
August 2021 – May 2023
- Machine Learning
- NLP/LLM
- Data Science
- Big Data Analytics
- Data Visualization
Bachelor of Engineering in Computer Science — Pune University (India)
August 2016 – June 2019
- Algorithms
- Data Structures
- DBMS
- Operating Systems
Associate of Science in Computer Science — Pune University (India)
August 2013 – June 2016
- Programming in C
- OOP
- Computer Networks
- Software Engineering
Technical Skills
Tools, systems, and strengths
Programming
- Python (NumPy, Pandas, Scikit-learn, Keras, TensorFlow, PyTorch)
- SQL, R, SAS, JavaScript, HTML/CSS
Databases
- SQL Server, PostgreSQL, Oracle, Snowflake
- Neptune, DynamoDB, MongoDB, PL/SQL
Machine Learning
- Regression, Classification, Clustering
- Hypothesis Testing, A/B Testing, Statistical Modeling
BI / Platforms
- Alteryx, Excel, Databricks, SSMS, DBeaver
- Power BI, Tableau, Streamlit, Looker, Qlik, Hugging Face, SSIS
Big Data & Cloud
- Apache Spark, Hadoop, Cassandra
- Azure, GCP, AWS (as used in projects)
Certifications
- Alteryx ML Fundamentals, AWS Solution Architect
- CAPM, DASM
LinkedIn
GitHub
Tableau