Data Analyst • Data Science • AI

Hi, I'm Krupa
Data Analyst & AI Professional

Data & AI professional with 3 years of data and software engineering experience and a Master of Data Science. I turn messy data into clear reports, dashboards and decisions people can trust, using Python, SQL, Power BI, Tableau and dbt.

Krupa

Turning messy data into clear insights

I am a Data & AI professional based in Melbourne, with 3 years of data and software engineering experience and a Master of Data Science from RMIT University. At Ribbon Communications I built Python and SQL automation and reporting that cut manual reporting effort by about 70%, and I set up validation rules and reconciliation checks so teams could trust their reports. As an AI Engineer at Kalibre, I designed and deployed a RAG knowledge platform that cut enterprise knowledge retrieval from around 30 minutes to near instant. I like making sure data is clean and correct, and explaining it clearly to technical and non-technical people. My work spans Python, SQL, Power BI, Tableau, dbt, machine learning, and cloud tools on AWS and Azure.

Name
Krupa Palani Ashoka
Degree
Master of Data Science with Distinction, Jul 2026
University
RMIT University, Melbourne
Email
pakrupa17@gmail.com
Location
Melbourne, VIC (open to relocating)
Status
Open to Data Analyst roles

Tech Stack & Tools

Tools I use to clean, model, analyse and present data, and to build intelligent, data-driven solutions.

Py
Python
Programming
SQL
SQL
Programming
BI
Power BI
Business Intelligence
Tb
Tableau
Business Intelligence
dbt
dbt
Data Modelling & Testing
Db
DuckDB
Analytics Database
Pd
Pandas
ML & Data
Np
NumPy
ML & Data
Sk
Scikit-learn
ML & Data
Stat
Statistics & Regression
Analytics
ML
Machine Learning
AI / ML
LLM
LLMs & RAG
Generative AI
LC
LangChain
Generative AI
Fx
FAISS & Vector Search
Generative AI
PE
Prompt Engineering
Generative AI
NLP
Natural Language Processing
AI / ML
Cv
Computer Vision
AI / ML
Fl
Flask
Web Development
AWS
AWS
Cloud
Az
Azure
Cloud
Dk
Docker
Cloud & DevOps
Git
Git & GitHub
Tools
CI
Jenkins & CI/CD
DevOps
Se
Selenium
Test Automation
SQ
SQLite
Data & Tools

What I've Built

A selection of projects across data analytics, business intelligence, data science, machine learning, and AI.

Data Analytics / dbt / Tableau
Does Rain Empty Melbourne's City Centre?

Analysed 1.6 million hourly footfall readings from 134 City of Melbourne street sensors with weather and public holidays. Built a tested dbt and DuckDB pipeline (14 data tests), measured what moves foot traffic (rain about -9%, heavy rain about -25%), and forecast daily footfall with a 6.6% average error. Published as an interactive Tableau dashboard.

dbtDuckDBTableauPythonRegressionForecasting
Business Intelligence / Data Analytics
Global Superstore Sales Dashboard

Designed an interactive Power BI dashboard for 51,290 fictional retail transactions, presenting sales, profit, order volume, category performance, geographic distribution, and yearly trends in a concise executive view.

Power BIData VisualisationDashboard DesignData ModellingBusiness Intelligence
Machine Learning / Regression
Melbourne Airbnb Price Prediction

Created an end-to-end regression workflow that predicts nightly Airbnb prices from listing, host, location, capacity, and review features using preprocessing pipelines and regularised linear models.

RegressionLassoFeature EngineeringScikit-learnPython
AI / LLM / RAG
NomadNest - Source-Grounded AI Travel Assistant

Built a local RAG assistant that retrieves evidence from official Australian sources and generates citation-backed travel guidance. The pipeline covers PDF ingestion, chunking, embeddings, topic-specific FAISS indexes, LangChain, Ollama, and a Streamlit interface.

RAGLangChainFAISSOllamaStreamlitPython
AI / NLP / Web Application
RecommenDress - Fashion Review Intelligence

Developed an end-to-end NLP application combining TF-IDF and logistic regression with a responsive Flask website. Users can search a clothing catalogue, browse reviews, and predict whether new review text recommends an item.

NLPTF-IDFLogistic RegressionFlaskScikit-learn
Machine Learning / Recommendation Systems
Movie Recommendation System

Implemented and evaluated five collaborative-filtering approaches on MovieLens 100K, including user-based, item-based, and hybrid KNN. The hybrid recommender achieved the best MAE and RMSE on a reproducible train-test split.

Collaborative FilteringKNNMovieLensPandasNumPy
Machine Learning / Multi-Class Classification
Wildfire Intensity Classification

Built a class-balanced machine-learning pipeline to classify wildfire intensity as Low, Moderate, High, or Extreme from geographic, temporal, weather, satellite, and fire-observation features.

SVMClassificationImputationFeature ScalingScikit-learn
Computer Vision / Deep Learning
Histopathology Cell Classification

Developed binary and multiclass cell-image classification workflows for colorectal histology data. Used patient-level splitting to prevent data leakage and implemented a reproducible CNN baseline for cancerous and cell-type classification.

Computer VisionCNNDeep LearningPatient-Level SplitPython
Machine Learning / Multi-Class Classification
Letter Recognition Classification

Trained Decision Tree and KNN models to classify capital letters A-Z from 16 image-derived features. Tuned the models with five-fold cross-validation and evaluated performance on held-out test data.

Decision TreeKNNCross-ValidationScikit-learnPython

Work Experience

Industry roles where I applied and grew my technical skills in real-world environments.

AI Engineer (Internship)
Mar 2026 - Jun 2026
Kalibre Pty Ltd - Melbourne, Australia
  • Designed and deployed an AI-powered knowledge management platform using RAG, Qwen 2.5, and Claude APIs, reducing knowledge retrieval time from approximately 30 minutes to near-instant responses.
  • Engineered end-to-end ingestion pipelines that transformed unstructured enterprise support data into searchable, embeddings-based knowledge assets.
  • Implemented vector-search and prompt-engineering strategies to improve response accuracy and reliability, then deployed the production solution on Azure.
  • Evaluated outputs against ground-truth queries to tune retrieval and prompting, improve answer relevance, and reduce hallucinations.
  • Collaborated with industry mentors and a multidisciplinary team to deliver the solution from pipeline design through production deployment.
RAGQwen 2.5Claude APIVector SearchPrompt EngineeringAzure
Senior Technical Analyst (Data Analyst)
Aug 2021 - Jul 2024
Ribbon Communications - Bengaluru, India
  • Built Python and SQL automation and reporting frameworks that reduced manual reporting effort by about 70%, freeing analyst time for deeper analysis.
  • Wrote complex SQL queries to extract, transform and analyse data across multiple sources for recurring reports and ad-hoc requests.
  • Supported the migration of on-premises data to Azure, including SQL Server updates through Azure Delta Load, and checked the data was correct before and after.
  • Put data quality controls in place (validation rules, reconciliation checks and documentation) to meet regulatory and company standards.
  • Automated data cleaning, transformation and reporting with Python scripts, and test automation with Selenium and Perl, improving turnaround on recurring deliverables.
  • Added automated reporting and validation suites to Jenkins CI/CD pipelines, improving accuracy and reliability across AWS and Azure environments.
  • Analysed integration results across Microsoft Teams Direct Routing, Ribbon SBCs and Twilio, found the root cause of data and system differences, and wrote clear reports for technical and non-technical stakeholders.
  • Worked with engineering teams to deliver reliable releases and explained data impacts to business stakeholders.
PythonSQLAzureData QualityJenkinsAWS

Education

Postgraduate study in data science and an engineering degree in information science.

With Distinction
Master of Data Science
RMIT University, Melbourne
2024 - Jul 2026

Coursework: Programming Fundamentals, Database Concepts, Applied Analytics, Data Wrangling, Big Data Processing, Case Studies in Data Science, Practical Data Science with Python, The Data Science Professional, Advanced Programming for Data Science, Artificial Intelligence, Algorithms and Analysis, Data Visualisation and Communication, Computational Machine Learning, Time Series Analysis, and the Data Science Postgraduate Project (industry project with Kalibre).

Bachelor of Engineering, Information Science & Engineering
Jyothy Institute of Technology, Bengaluru
2017 - 2021
RMIT University testamur: Master of Data Science with Distinction, awarded 31 July 2026 RMIT testamur - view full size

Let's Connect

I'm looking for Data Analyst and Data Science roles, including work with AI and machine learning, and I'm happy to relocate. Feel free to get in touch.