Data analyst with work experience in the banking industry equipped with credit analytical skill, risk and compliance knowledge.
This project focuses on the classification of twitter text based on their corresponding labels (gender). Models used were ensemble model, logistic model, support vector classifier (SVM) and XGBoost.
This project is an analysis on the forest fire data in Portugal. Statistical evidences were used to identify the subset and assessed with cross-validation. Models used for prediction were linear regression, XGBoost and XGBoostLasso models.
This project is an analysis on the rain in Australia. Pyspark.sql libraries were used to query the data from the database. Machine learning algorithms consisting of decision tree, random forest, logistic regression and gradient boosting were applied.
This is an exploration and visualisation project to understand the effects of Airbnb on the neighbourhoods in Melbourne. The exploration was done with Tableau while the visualisation was demonstrated on R Shiny and R Plotly.
This project is an analysis on South Australia's crime data from 2010 to 2019. MongoDB was used as a data source with Spark dataframe used to hold the data from the database along with Python's Matplotlib to construct the visualisations.
This project is an analysis on South Australia's crime data from 2010 to 2019. MongoDB was used as a data source with Spark dataframe used to hold the data from the database along with Python's Matplotlib to construct the visualisations.
This project is an analysis on Uber Data which contained incorrect values, missing data and outliers.Manipulation of data was done using Python Panda library while predictions from Python sklearn was used to input missing values.
This project is a preprocessing task on the unit guides in Monash University. Relevant details are extracted from the text file using regular expression and exported form of xml and json file. A vocab file was also produced to obtain the count of
This project is an integration of data of Victoria suburb boundary, crime by location of suburbs and gfts folder to obtain an overview of the suburbs in Melbourne in terms of price, crime rate, distance to train station and travel time to the city.
Using confidence interval and hypothesis testing for printing company case.Linear regression model was used to identify which components of the process were causing the roughness problem faced by the printing company.
In this project, I have created tables and constraint definitions in the database. I've also managed transactions based on the task provided.
Performed normalisation based on data and created a logical level design for Monash Cabins database. A schema was created to create the database in Oracle account.
Key Responsibilities:
• Extracted and manipulated data from a variety of sources to obtain cleaned dataset using Python.
• Created visualisation and dashboard using Tableau and PowerBI to provide users an accessible way to see and understand trends.
• Developed machine learning predictive models to obtain specific output and dataset.
Key Responsibilities:
• Automated data visualisation process which reduced reporting time by 3 hours.
• Interpret trends or patterns in complex data sets and analyze results using statistical techniques to provide ongoing reports
• Developed and maintained databases by extracting data from primary and secondary sources
Key Responsibilities:
• Designed and developed a new financial template which had enhanced the accuracy of credit profile assessment on the bank's counter-parties by 90%.
• Identified relevant insights and compiled analytical reports that enable sound decision making.
• Created a credit rating dashboard in collaboration with credit rating agencies which was used as an indicator to manage and forecast the bank’s credit risks. This has reduced the bank's credit risk by 80%.
• Enhanced the credit limit dashboard to track limits of products provided to the bank’s counterparties which prevented single counterparty exposure limit from being breached.
• Conducted Know Your Customer (KYC) , Anti Money Laundering (AML) and Customer Due Diligence (CDD) process on ongoing and onboarding institutional clients which ensured that customers are risk compliant.
Key Responsibilities:
• Classified and forecasted potential sources of competitive advantage through analysing data of competitors in the market.
• Identified market trends and analysed results to provide ongoing marketing reports.
• Utilised data and researched to identify new product development.
• Involved in the initial planning of the launch of retail products by the bank.
Years of Work Experience
• Python
• R
• SQL
• MongoDB
• Tableau
• Spark
• PowerBI
• Microsoft Excel