.jpg){kind=link}
"Don't let what you think you can’t do interfere with what you can do."
Oct 2024 - now - Finance Transformation Analyst, Finance & Controlling - Haventree Bank - Toronto, Ontario, Canada 🍁🇨🇦
Apr 2024 - Oct 2024 - Analyst, Business Insights, Accounting, Tax & Finance - Hudson's Bay Company - Toronto, Ontario, Canada 🍁🇨🇦 🇺🇸
- BI Solution Development: Led & coordinated monthly projects with Data Engineer and Architect to reduce processing time by 70-95% through Alteryx, Python, Power BI, saving costs at US$20,000/activity, previously managed by consulting firms.
- Revenue Optimization: Increased tax recovery chance by 10-30% of presumed yearly recoverable tax at CA$1 million and improved tax compliance by 10-40% per month using data-driven strategies with diagnostic modeling and forecasting.
- Cross-Platform Integration: Integrated Sales Audit, Online Management, Credit Sales Ledger, Tax Systems, Snowflake, Oracle, Vertex data into a deployable Snowflake Tax Data Hub with Alteryx, Python, Tableau, Power BI, and SQL, enhancing revenue & tax reporting accuracy by 5-30% and increasing tax recovery chance for retail sales and order return data monthly by 2-8%.
- Advanced Resolutions: Applied multi-layer predictive modeling to guide risk mitigation strategies with AI, achieving 80-95% precision in categorical text analysis and extraction, while increasing Tableau, Power BI viewer engagement by 10-25%.
Jan 2024 - Dec 2027 - Master of Liberal Arts (ALM), Extension Studies, Harvard University, Admitted Candidate - Harvard Extension School, Harvard University (online part-time) - Cambridge, Massachusetts, USA 🇺🇸
Jan 2023 - Apr 2024 - Alteryx Administrator, AWS Cloud Ops Data Migration - Billennium IT Inc for Roche (Swiss BioTech), Data Engineering - Integration, Data Services & Insights Foundational Domain - Mississauga, Ontario, Canada 🍁🇨🇦
- Data Systems Management: Monitored, managed North American and European users' access with workflow hubs, data storages, Alteryx usage while documenting users' activities to ensure compliance with global Roche data protection standards.
- Technical Solutions: Maintained and upgraded Alteryx servers to optimize performance and ensure data accuracy across the organization, collaborating with stakeholders across North America and Europe.
Jan 2021 - Aug 2022 - Business Insights & Analytics Post-Graduate Program - Humber College - Toronto, Ontario, Canada 🍁🇨🇦
May 2022 - Aug 2022 - Data Science Intern (remote) - Cohost AI (founded in San Francisco, USA, based in Ha Noi, Viet Nam) - Toronto, Ontario, Canada 🍁🇨🇦
- Revenue Forecasting: Delivered 40-60% more accurate forecasts, optimizing revenue management metrics & KPIs in Python.
- Dashboard Innovation: Developed interactive Power BI dashboards, boosting stakeholder and user engagement by 10-25%.
Jan'22 - Apr 2022 - Product Data Analyst Intern - iRestify Inc. (based in Toronto, Canada) - Toronto, Ontario, Canada 🍁🇨🇦
- Revenue Forecasting and Visualization: Developed Power BI dashboards to analyze Geographical Information System (GIS) data for revenue management and commercial KPIs, leading to a 15% increase in user productivity and a 20% improvement in stakeholder compliance, which boosted operational standards and increased customer success rates by 15%.
Aug-Dec 2021 - Data Engineering & Analytics Intern (remote) - Center of Talent in AI (CoTAI, based in Ho Chi Minh City, Viet Nam) - Toronto, Ontario, Canada 🍁🇨🇦
- Data Pipeline Optimization: Streamlined data retrieval processes through the development of efficient data pipelines from South East Asia to North America, supporting Sentiment Analysis initiatives in SQL, Python, Tableau while maintaining the organization’s data security and privacy.
- Compiled Machine & Deep Learning classifiers tackling imbalanced datasets to detect fraud for Banking’s Marketing Targets
Jun 2017 - Jun 2019 - Sales Executive & Sales Coordinator - Sofitel Saigon Plaza - Ho Chi Minh City, Viet Nam
- Revenue Forecasting: Prepared, consolidated financial Excel & Power BI reports to track sales performance and forecast departmental revenue targets, supporting executive decision-making and driving quarterly sales growth by 1-10% per account.
- Revenue Generation: Managed key accounts, segments, and markets, consistently meeting and exceeding team & personal revenue targets for approximately 16 months, contributing to 65% of sales duration while consulting with the Revenue team on target settings.
| Topic | more projects available on GitHub & Tableau Public |
|---|---|
| IEEE-CIS Fraud Detection (Capstone, Humber College) | - Preprocessed data in Python, designed architecture solution, analyzed performance between ML classifiers to determine the best performers on the imbalanced dataset, Balanced Random Forest with ROC AUC around 0.9 & Random Forest with ROC AUC, Precision around 0.9 |
| Safe Roads 2022 Competition - Toronto Police Service | - Used Power BI, Python, Azure Machine Learning to analyze geospatial datasets, provide interpretation, conduct A/B testing, determine factors, recommend on road conditions, awareness, top fatal intersections to enhance traffic safety, prevent fatal accidents, achieve prediction using Random Forest’s ROC AUC & Precision around 0.8 |
| Sentiment Analysis | - Conducted Sentiment Analysis on customer’s comments & analyzed data generated from a system using Natural Language Processing through API on Fan Pages’ dialogs of diet products & participated in Data Operations, ETL in Python, SQL in MySQL, Azure, Visualization in Tableau to determine top customers, top efficient fan pages, most crucial intentions & demand entities, peak effective contact hours, peak periods of confirmations, common complaints |
| Banking Dataset – Marketing Targets | - Used classification methods of ML, DL in Python to predict more accurately filing a claim while avoiding overfitting on an imbalanced dataset; - RUS Boost had the highest Balanced Accuracy, Geometric Mean, F1 scores & best Confusion Matrix among classifiers |
| SQL Murder Mystery | - Determined the extract murder and killing planner with the shortest-possible SQL queries from basic to intermediate querying skills & approaches using: INNER/LEFT JOIN, GROUP BY, WITH, WHERE, Sub-Queries |
| Porto Seguro’s Safe Driver Prediction | - Used classification methods of ML, DL in Python to predict more accurately auto insurance policy holders filing a claim (predict the probability) while avoiding overfitting on imbalanced dataset - RUS Boost had the highest Balanced Accuracy, Geometric Mean, F1 scores & best Confusion Matrix among classifiers |
| Acquisition & Merger Analysis | - Compared techniques between loading dataset in Python’s SQL Alchemy to MySQL & loading it in SQL to Hadoop, investigated & identified organizations for the most profitable merger and acquisition by examining accumulated data sets in terms of Sales, Revenue, Product Line in SQL on Zeppelin, visualized charts in Tableau, Power BI |
| Pharma Portfolio Predictive Analysis | - Coded in Python and AzureML to analyze time-series pharmaceutical sales data and forecast the key pharma product and predict the patterns in the future |
| Annual Sales Analysis & Visualization | - Applied EDA in Python, visualized 200K datapoints to answer Revenue questions - Visualized & compared results between charts in Tableau & Power BI to determine that the variables which caused the highest Sales Value: December, San Francisco, peak hours placing orders, top sold products, correlation between Prices & Volumes |
| Income Analysis & Classification | - Preprocessed, analyzed the Income background of all records in Python, SQL & visualized key variables in Tableau / Power BI to determine highlights, trends & predictions of Income types with ML, DL Classifiers |
| Eden Hotels & Resorts Group | - Created a Sales Incentive Plan in Java: input, check password, calculate Salespersons, Revenues & export reports, calculated Hotel Revenue’s metrics in Excel to analyze, visualize different types of KPIs - Designed Database and inserted sample data into tables of hotels, guests, employees & bookings in SQL queries |
| University Admission | - Led a team & built a Java program (< 150 coding lines) to store information of the newly admitted students, prompted user to enter the student name & high school grades, calculated GPA & assigned to the University’s schools |
| Investment Analysis of Shopify and Lightspeed in Canada | - Managerial Finance & Accounting Report |
| Governance & Ethics in Data | - Gained the highest grade of 95% in all Professor's classes analyzing ethics & governance models about data manipulated in Cybersecurity, COVID-19, Vaccination, etc. - Analyzed 3 aspects of the ethics model, data governance to mitigate potential challenges in the chosen context |
| TD Bank's Porter’s Value Chain Analysis (available for being shown only in a section) | - Conducted an analysis of TD Bank over history, vision, mission, strategic and financial objectives, External environment based on PESTEL and Five Forces analysis, Internal environment based on SWOT-analysis, resource and capability analysis, and a value chain analysis, the current strategic approach and its various strategic actions, the staffing practices and strategy execution, Organizational structure. |
| Better Working Word - EY, NASA, Microsoft | - Using Python, Machine Learning, Azure Studio, Azure Machine Learning in 3 challenges for 3 months to help locate and protect the biodiversity of frogs by discovering and counting local and global frogs on weather data sampled over space and time (spatiotemporal sampling) with given preliminary F1 score. |
| US Medicaid Pharmacy Pricing Analysis | - Establishing tables by nodes and Graph on Neo4j in Cypher, and on Azure in SQL to predict future prices/quantities and important pharmaceutical products of US Medicaid datasets in Python, AzureML |
| Home Credit Default Risk | - Connected, transformed datasets, conducted EDA in SQL, Scala on Hive, Zeppelin on customized datasets on the to analyze the loan applicants' background and help expanding to those unable to access financial services - Determined on Zeppelin/ Tableau/ Power BI the most significant background check of applicants who got most loan approvals |
| Courses | Details |
|---|---|
| Data Analytics Tools ✅ | SAS, SPSS Modeler, SPSS, Excel, Cognos |
| Managerial Finance & Accounting ✅ | Excel (Investment Analysis of Shopify and Lightspeed in Canada) |
| Big Data ✅ | Hadoop, R, Neo4j, Cypher, Graph |
| Quantitative Research Methods I & II ✅ | Descriptive & Inferential Statistics, Probability, Normal Distribution, Estimation, Hypothesis Testing |
| Database & SQL ✅ | SQL, ERD, Normalization |
| Governance & Ethics in Data ✅ | Reflection & Integration of Knowledge: Governance & Ethics of Analytics in in Data, AI & Technology - only available from hyperlink in my Resume - (graded 95/100 & feedbacked by Professor. Kathleen Mcginn 😧 : "My goodness Phuong,Thank you for sharing this with me. It is indeed a very deep, intelligent and meaningful piece of writing that deserves an excellent grade - 95 (!) - the highest grade I have given so far. Congratulations - you have truly earned it.") |
| Canadian Business & Strategy ✅ | TD Bank's Porter’s Value Chain Analysis & Nucor Corporation Analysis |
| Marketing ✅ | |
| Predictive Analytics ✅ | linear and multiple regression, decision trees, linear programming, factor analysis, cluster analysis, modelling |
| Machine Learning and Programming 1 & 2 ✅ | Python: Data Mining, Data Science, Data Visualization, Dimension Reduction, CRM, Evaluation Predictive Performance, Multiple Linear Regression, K-NN, Naives Bayes Classifier, Classification, Regression Trees, Logistic Regression, Cluster Analysis |
| Communication & Data Visualization ✅ | Excel, Tableau |
| Business Intelligence ✅ | Power BI |
| Machine Learning and Programming 2 ✅ | Python: Time Series Forecasting, Market Basket Analysis, Natural Language Processing |
| Capstone Course ✅ | IEEE-CIS Fraud Detection (Capstone, Humber College) |
| Project Management ✅ | Boeing Aviation Case Report of Sales and Supply Boost |
| Criteria | Details |
|---|---|
| Programming | Certified SQL, Python (Pandas, Numpy, Matplotlib, Keras, SkLearn), Tensorflow Developer (in progress), T-SQL, PL/pgSQL, Java, Scala, R, HTML |
| Viz & ETL | Certified Power BI, Tableau Desktop, Alteryx Advanced Designer, Alteryx Designer Cloud Advanced, Alteryx Machine Learning Fundamentals, Tableau Prep, SPSS (Modeler, Statistics), SAS (Studio, Enterprise Miner), Cognos, Qlik |
| Big Data | Certified Azure Data Fundamentals, Azure AI Fundamentals, Alteryx Server Administration, Databricks Accredited Lakehouse Fundamentals, AWS (ML & Data Analytics), Azure (ML, Synapse), MySQL, MongoDB, MS SQL, Oracle, PostgreSQL, Hadoop (Hive, Zeppelin), Neo4j, Splunk |
| Collaboration wiki | Atlassian Confluence, Jira, Trello |
| Languages | English 🇺🇲 (fluent), Vietnamese (native), French 🇨🇦🇨🇵 (basic overall, intermediate reading), German 🇩🇪 (basic overall, intermediate reading) |
| Others | Certified Six Sigma White Belt, Excel (Solver, GoalSeek, Macros), GDPR, ServiceNow, Confluence, Jira, Trello, Machine & Deep Learning, AI, Teamwork, Statistics, Probability, Sales, Accounting, Finance, Project Management, Hospitality, Presentation, Communication, Marketing |
| Earned 🏅 | Details |
|---|---|
| ProtonX | Tensorflow Developer (Statistics, Probability, Algebra, Machine Learning, Deep Learning, AI) |
| Center of Talent in AI | Python, Machine Learning, Deep Learning, AI, Reinforcement Learning |
| Nordic Coder | Python, Tableau |
| DataCamp | SQL Intermediate |
| Microsoft Office Specialist | Word, Excel, Powerpoint |
| Udemy | Power BI for Business Intelligence |