About Me
Data Scientist with years of experience analysing large datasets, uncovering insights to make informed decisions. Strong background in designing and implementing scalable data processing pipelines and utilizing container…
Data Scientist with years of experience analysing large datasets, uncovering insights to make informed decisions. Strong background in designing and implementing scalable data processing pipelines and utilizing containerization to enhance efficiency and reliability. Implemented machine learning models to identify false positive from large and complex datasets. Worked with high-profile clients across a multitude of sectors, leveraging analytical and data reporting skills to extract meaningful trends in support of data-driven, decision-making opportunities, saving up to $100k+ in erroneous transactions. Developed BI solutions setting up data pipelines for real-time dashboards.
Experience
Senior Python Data Engineer
Part of the Data Analytics and Engineering team, developing data pipelines, automating data ingestion for payroll, timesheets, and leaves data. The team heavily focuses on R&D to develop pipelines for efficient data ingestion.
• Developed and configured data pipelines for wage remediation for host of high-end retail clients. Used Yaml file configurations to standardise the pipelines using Luigi, an open-source Python framework for workflow management and building pipelines.
• Completely revamped the wage remediation dashboards for executive and managerial level audiences and presented to the wider team and CEO, using advanced Tableau features and visualisation techniques.
• Managed and delivered data ingest for multiple projects, streamlined using Docker environments.
• Conducted extensive data analytics in liaison with the customer teams utilising skill of communicating with cross-functional teams.
• Ensured successful and on time delivery of major wage remediation projects liaising with the data team and customer team.
• Extensively used Python based solution to automate some of the repetitive tasks.
• Other tasks: Git actions, Automated Sphinx documentation, Testing, PR Reviews
Senior Python Engineer
Developed and configured data pipelines for wage remediation for host of high-end retail clients.
Used Yaml file configurations to standardise the pipelines using Luigi, an open-source Python framework for workflow management and building pipelines.
Completely revamped the wage remediation dashboards for executive and managerial level audiences and presented to the wider team and CEO, using advanced Tableau features and visualisation techniques.
Managed and delivered data ingest for multiple projects, streamlined using Docker environments.
Conducted extensive data analytics in liaison with the customer teams utilising skill of communicating with cross-functional teams.
Ensured successful and on time delivery of major wage remediation projects liaising with the data team and customer team.
Extensively used Python based solution to automate some of the repetitive tasks.
Other tasks: Git actions, Automated Sphinx documentation, Testing, PR Reviews
Data Science | Python Engineer
Developed a robust program for financial calculations in Java to calculate IRR and NPV for cashflows.
Developed a Streamlit front-end with Python.
Leveraged libraries for effective implementation of an automated cost plan.
Streamlined code, minimised the script by reducing from 10000+ lines of code to only 4000 lines of code.
Made the code repeatable and robust.
Liaised with the cost planning team to work on Benchmarking for cost planning.
Developed database strategy to migrate the finance data model from an unstructured NoSQL database to a relational one.
Developed database model for Finance Service in the Envision Product.
Data Analyst
Implemented a statistical rigor in the dashboards containing information about customer dissatisfaction scores.
Provided statistical insights relating to the DSAT scores based on different RSPs, Technologies, Drivers etc. by creating interactive visualisations.
Performed BAU tasks including Alteryx workflows and Tableau dashboards for timely reporting to a wider audience.
Data Science | Python Developer
Developing a Natural Language Generation (NLG) framework for automated commentary on data and dashboards.
Working with Arria NLG studio to deliver self-service analytics for a variety of end users with different needs.
Developed a machine learning strategy to predict new business conversion with motor insurance data.
Guided colleagues on machine learning methodologies and appropriate use of algorithms based on situations.
Developed a data access solution for cost centre managers for transactional data, with extensive use of SQL and Python, with a simplistic front end.
Developing Gross Written Premium dashboard in Tableau environment for efficient delivery of information.
Developing Python based solution to automate some of the repetitive tasks.
Data Science | Solutions Consultant
Developed Machine Learning strategy to identify false positives for clients: Healthscope and Qantas, to target relevant exceptions.
Consulted with and provided data analytics expertise on the customisation and integration of the SatoriCCM to Flight Centre, Worksafe Victoria, JB Hi-Fi, Optus, Auckland Council, Origin Energy, and more.
Revamped Flight Centre’s Python scripts (6 reports consisting of 12 scripts).
Consolidated all data into one master script with dynamic wait times and repeatable and concise code.
Visualised data using dashboards and storyboards to better communicate the insights through the customisation of Galvanize Storyboards, Dundas BI, and Excel.
Manipulated data in the CCM backend (an SQL Server database) including optimising SQL queries and commands for better performance.
Optimised SQL queries for Origin that resulted in previous reports that would take over 90 seconds now being delivered under 5 seconds.
This new SQL framework is fully customisable and delivers greater scalability.
Delivered new Robots Projects helping to get more customers onto this platform with accountability for installing and administering the Robot Agent as well as providing training to other consultants.
Conducted in-house trainings for colleagues on the analytics software and automation tools.
Data Analyst (Contract)
Analysed data sets of over 350,000 potential clients with revenues of $1Mil-$10Mil+ with the aim of creating a target list of dates that would aid sales team in driving new business opportunities.
Implemented a Python Selenium module to automate the profiling process along side of LinkedIn Sales Navigator and Lusha.
This automated the process to capture intelligence and data of 3,000 existing accounts.
Conducted extensive data analysis and reporting utilising MS-Excel incl. Vlookups, Pivot Tables and Charts.
Integrated data for three teams into one master sheet to be used for cross collaboration.
Data Analyst | Database Developer
Designed a project prototype using Excel for effective database development.
Used Lookup functions (Vlookups), advanced formatting and pivot tables to analyse sales data of 3 months for ITBS.
Implemented Elastic Stack for real-time evaluation and correlation of Windows logs and events.
Configured files for parsing log data using Logstash for storing and indexing in Elasticsearch.
Set up Kibana Dashboards to visualise events such as error, critical, warning and security threats.