Open to work  ·  Auckland, NZ

Dario Dang

Data Scientist

Building end-to-end ML pipelines, geospatial models,
and real-time analytics systems with Python, PySpark & SQL.

View Projects Get in Touch

Tech Stack

Languages

PythonSQLRJavascriptHTMLCSS

ML & Data

scikit-learnPySparkMLflowXGBoostK-MeansSk-Learn

Cloud & Infra

AWS RedshiftAWS S3AWS RDSdbtDockerPrefectPgAdminPostgres

Visualisation

MatplotlibSeabornGrafanaPower BIStreamlitPlotly

Geospatial

GeoPandasQGISFMEARCGIS

Other

GitRAG / LLMsSAPSEO

Projects

A selection of data science projects from live dashboards to ML pipelines.

NZ Electricity Dashboard View Live ↗
APIDashboardReal-time

NZ Electricity Dashboard

Real-time NZ electricity market dashboard consuming the em6 API — tracks live pricing, generation mix, and demand.

Retail Price Intelligence Dashboard View Live ↗
ETL PipelineAutomationDashboard

Retail Price Intelligence

Automated daily scraping pipeline across NZ electronics retailers, ingesting 200+ products at 8pm NZT with trend visualisation.

Christchurch FoodieBot RAG system View Live ↗
RAGLLMStreamlitLLM Evaluate

Christchurch FoodieBot

RAG-powered chatbot over Google & Yelp reviews — answers natural language questions about 100+ Christchurch restaurants.

Chicago Taxi MLOps pipeline View Project ↗
MLOpsMLflowPrefect

Chicago Taxi MLOps

End-to-end ML pipeline predicting taxi ride duration on 1M+ records, with MLflow experiment tracking and Prefect orchestration.

Student retention classification model View Project ↗
ClassificationStatisticsEducation

Student Retention Model

Classification model identifying at-risk university students using cohort features, achieving strong precision on held-out test data.

Geospatial crash hotspot modelling View Project ↗
GeospatialMLGeoPandas

Geospatial Crash Modelling

Spatial clustering and hotspot analysis on NZ road crash data using GeoPandas, DBSCAN, and interactive Folium maps.

Million Songs PySpark genre classification View Project ↗
PySparkBig DataRecommendation

Million Songs — PySpark

Genre classification and audio similarity recommendation across 1M+ tracks using PySpark and collaborative filtering at scale.

Worldwide precipitation trend analysis View Project ↗
Time SeriesGeospatialClimate

Precipitation Analysis

Processing, analysing, and forecasting global precipitation trends using time series modelling and spatial interpolation.

Customer segmentation RFM K-Means pipeline View Project ↗
K-MeansRFMClustering

Customer Segmentation Pipeline

RFM + K-Means pipeline segmenting e-commerce customers into behavioural cohorts to drive targeted marketing strategy.

NYC Taxi Power BI and dbt dashboard View Project ↗
Power BIdbtRedshift

NYC Taxi — Power BI

Power BI dashboard connected to a Redshift + dbt pipeline, tracking NYC taxi KPIs across 500K+ monthly trips.

Healthcare prediction Streamlit ML app View Project ↗
StreamlitMLHealthcare

Healthcare Prediction App

Interactive Streamlit application combining multiple ML models for predictive healthcare diagnostics with live inference.

About Me

Portrait of Dario Dang

I'm Dario Dang, a Data Scientist based in Auckland, NZ with a Master of Applied Data Science from the University of Canterbury. I bring a strong foundation in statistics, machine learning, and software engineering to every project I work on.

My work spans the full data lifecycle from ingesting and transforming raw data to building production-grade ML models, geospatial pipelines, and real-time analytics systems. I care about solutions that are not just accurate, but scalable, reproducible, and interpretable.

I'm actively seeking Data Scientist and Data Analyst opportunities in New Zealand where I can contribute to meaningful, data-driven decisions. I thrive in collaborative environments and enjoy turning complex problems into clear, actionable insights.

Courses & Certificates

Master of Applied Data Science
Master of Applied Data ScienceUniversity of Canterbury
 MLOps Zoomcamp
MLOps ZoomcampDataTalks.Club
 Machine Learning for Data Analytics
Machine Learning for Data AnalyticsUniversity of Science
 Python for Data Analytics
Python for Data AnalyticsUniversity of Science
 SQL for Data Analytics
SQL for Data AnalyticsUniversity of Science
 Feature Manipulation Engine (FME)
Feature Manipulation EngineSafe Software
 BA Business and Marketing
BA Business & MarketingBachelor's Degree
Advanced Python DataCamp
Advanced PythonDataCamp

Activities

Master's Capstone Presentation at University of Canterbury
Academic

Master's Capstone — University of Canterbury

Presented a complete end-to-end data science solution to an academic panel as part of the Master of Applied Data Science program, covering data collection, exploratory analysis, ML modelling, and insights communication. Developed skills in research, critical thinking, and presenting complex technical findings to a professional audience.

University basketball team captain
Leadership

University Basketball Captain

Led a university basketball team, coordinating training schedules, mentoring teammates, and driving team strategy. Strengthened leadership, communication, and collaborative problem-solving skills under competitive pressure.

Get In Touch

I'm currently open to Data Specialist and Analyst roles in New Zealand.
Whether it's a role, a project, or just a chat, feel free to reach out.

Say Hello 👋
GitHub LinkedIn Download CV