Hello, my name is Muhammad Enrizky Brillian

I' m a Machine Learning / AI Engineer, Consultant

Muhammad Enrizky Brillian builds production AI systems that deliver measurable business outcomes. As a Machine Learning / AI Engineer, Consultant at IBM, he has architected multi-agent pipelines achieving 93% accuracy for $300K+ contracts and deployed multimodal RAG solutions with 97% answer relevancy across AWS and Azure. His research at Toronto General Hospital produced a multi-agent LLM predicting transplant-free survival with 88.7% accuracy across 1,260 patients at 32 US centers. At Sanofi, he engineered ETL pipelines processing billions of records from an $800M vaccine plant, replacing days of manual work with seconds. From deep learning on 122 GB pathology datasets to cross-platform React/React Native applications, he works across the full AI stack: PyTorch, TensorFlow, LangChain, HuggingFace, and AWS.

Download CV

About Me

I'm Muhammad Enrizky Brillian as a Machine Learning / AI Engineer, Consultant

Machine Learning / AI Engineer, Consultant at IBM, where I architect and deploy multi-agent AI systems across AWS and Azure. I built a Text-to-SQL pipeline (93% accuracy, $300K+ contract), a multimodal agentic RAG solution (97% answer relevancy), and a cross-cloud interoperability platform using the A2A protocol that reduced API calls by 73%. I also built an agentic browser framework that outperforms existing tools by 3x on cost and 20% on speed through DOM-first extraction. At Toronto General Hospital, I engineer deep learning pipelines for 122 GB of pathology data and developed a multi-agent LLM achieving 88.7% accuracy on 1,260 patients across 32 US centers. At Sanofi, I processed billions of manufacturing records and replaced days-long workflows with a two-click Snowflake/Streamlit solution. Proficient in Python, PyTorch, TensorFlow, LangChain, AWS, Docker, React, and TypeScript.

Website : https://billy-enrizky.github.io/portfolio/

Email : billy.suharno@gmail.com

Degree : Honours Bachelor of Science with Co-op, Data Science and Machine Learning Specialist, Computer Science Major, Economics Minor — University of Toronto (High Distinction)

Phone : +14167317583

City : Toronto, Ontario

Hire Me
Applied Deep Learning & Machine Learning
94%
Computer Vision
97%
Data Extraction, Transformation, Loading
96%
Data Visualization
93%

Education

Georgia Institute of Technology — Master of Science in Computer Science, Specialization in Artificial Intelligence

Courses: Deep Learning, Computer Vision, Natural Language Processing, Knowledge-Based AI, Software Development Process, Quantum Computing.

University of Toronto — Honours Bachelor of Science with Co-op, with High Distinction

Data Science and Machine Learning Specialist (Co-op), Computer Science Major, Economics Minor.

Accepted to 3 graduate programs: Fully Funded MSc/PhD at Institute of Medical Sciences (University of Toronto), MSc Applied Computing AI Specialization at Department of Computer Science (University of Toronto), and Master of Data Science and AI at University of Waterloo.

Courses: Advanced Machine Learning and Data Mining, Analysis of Big Data, Multivariate Analysis, Probability & Stochastic Processes, Regression Analysis, Statistical Inference, Algorithm Design and Analysis, Discrete Mathematics.

Experience

May 2025 - Present

Machine Learning / AI Engineer, Consultant at IBM (International Business Machines), Toronto, ON

  • ● Engineered end-to-end multi-agent Text-to-SQL solution on AWS (App Runner, VPC, ECR, Bedrock, OpenSearch, Redis), achieving 93% accuracy in 8 weeks and delivering over $300K contract value for an enterprise client.
  • ● Built cross-platform UI with React/TypeScript for web and React Native/Expo for mobile, enabling unified access across web browsers, iOS, and Android through a shared component library.
  • ● Developed multimodal agentic RAG pipeline unifying image and text databases with agentic PDF parsing and reranking, delivering 97% answer relevancy and cross-modal retrieval across document formats in four weeks.
  • ● Built cross-cloud multi-agent interoperability platform via A2A protocol, bridging Azure Foundry, AWS Bedrock AgentCore, and LangGraph agents through Entra ID JWT, deploying 5 domain agents with 73% reduction in API calls.
  • ● Researched and engineered agentic browser framework OpenBrowser for SAP enterprise automation using CDP and MCP after benchmarking 6+ tools, outperforming state-of-the-art by 3x lower cost and 20% faster through DOM-first extraction.
  • ● Engineered transaction-level P&L rebuild pipeline in Python for an enterprise finance client, reconciling EBITDA across 15 entities (SAP, ECC, QuickBooks) with 67 rules; delivered BigQuery warehouse, LookML semantic layer, and Next.js copilot with Vertex AI Gemini.
  • ● Deployed Gemma 4 31B on SageMaker (4x A10G) for a regulated heavy fabrication client with 5-knowledge-base RAG on Bedrock, achieving 6x speedup (12 to 2 min) via ThreadPoolExecutor; built dual Flask microservices with WAF geo-lock to Canada.

Jan 2024 - Aug 2025

Data Scientist at Sanofi

  • ● Built the ETL pipeline (Top 1 Contributor on GitHub) using Python (NumPy, Pandas) and SQL, integrating billions rows of data from the largest vaccine production plant in Canada, worth $800 millions of dollars.
  • ● Engineered two-click, self-service workflow on Snowflake (warehouse & deployment) and Streamlit (Front-End User Interface), slashing manual data-entry cycles from several days to seconds.
  • ● Led a cross-functional team of data engineers, enhancing team productivity by 40% through agile methodologies and automated process, contributing to data infrastructure strategic planning.

Sep 2024 - May 2026

Machine Learning Research Student (T-CAIREM Research Award) — Toronto General Hospital, UHN

Supervised by Dr. Mamatha Bhat and Dr. Joseph S. Kim.

  • ● Engineered end-to-end deep learning pipeline from image encoding, finetuning, and inference for 122GB pathology whole-slide images on Linux-based supercomputers with HuggingFace foundation models and custom multi-scale segmentation architectures.
  • ● Enhanced model accuracy from 56% to 71% by selecting various ML models from Scikit-learn and XGBoost and tuning hyperparameters across learning rate, tree depth, and regularization through exhaustive Grid Search CV with stratified cross-validation.
  • ● Engineered end-to-end deep learning multimodal model combining clinical text embeddings and histopathology image features using early fusion for predicting steroid responsiveness in liver transplant rejection across 55 patients with biopsy-confirmed TCMR.
  • ● Developed multi-agent large language model system for predicting 21-day transplant-free survival in acute liver failure, achieving 88.7% accuracy and 95.1% specificity across 1,260 patients from 32 US centers.

May 2025 - Aug 2025

Full Stack Developer Intern — Leslie Dan Faculty of Pharmacy (LDFP), University of Toronto

Supervised by Professor Mina Tadrous.

  • ● Built paper-screening agent integrating various LLMs (OpenRouter, Gemini, OpenAI) and ingesting diverse formats (CSV, RIS) to evaluate complex eligibility criteria with pydantic schema enforcement across title, abstract, and full-text stages, achieving 92% accuracy.
  • ● Developed full-stack platform using NodeJS, ExpressJS backend and NextJS, React, TypeScript frontend with in-app messages, pharmacist-patient matching algorithms, and proximity-based geographic filtering, targeting $12.5M annual savings.

May 2025 - Aug 2025

Research Student at Acceleration Consortium

  • ● Implemented scalable machine learning pipeline, leveraging OpenCV, Pandas, and MediaPipe hand detection to process 60 high‑resolution (7 GB each) videos and extract key reproducibility metrics.
  • ● Engineered multimodal AI data extraction pipeline leveraging GPT-4 Vision and PyMuPDF to process over 10K pages of PDFs, achieving 99.98% accuracy, generating over 10K rows of 22-field structured CSV.

May 2024 - Aug 2024

Research Student at University Health Network (UHN), KITE Research Institute

  • ● Performed comprehensive data preprocessing for human action recognition video datasets, optimizing for Few-shot Deep Learning models and enhancing applicability in industry settings.
  • ● Evaluated the generalization ability of the deep learning models by conducting cross-dataset testing on Ubuntu-based supercomputers, achieving accuracy over 68% accross different settings.
  • ● Created and presented research poster at the Data Sciences Institute, demonstrating strong technical writing and communication skills to effectively convey research findings.
  • ● Developed a flexible Siamese Neural Network adaptable to various backbone architectures, using PyTorch, achieving approximately 88% accuracy in Spatial Temporal Relation Modeling.

Sep 2022 - Dec 2022

Big Data Analyst at Kimia Farma

  • ● Engineered a SQL database with 140,000+ entries and 30+ columns, optimizing access across 20+ branches, resulting in a remarkable 70% boost in sales distribution efficiency.
  • ● Leveraged SQL querying expertise to optimize data ETL, leading to a 33% reduction in data processing time, and directly contributed to a 40% reduction in operational cost.
  • ● Designed and developed a Tableau dashboard for sales data, enhancing data accessibility and facilitating data-driven decision-making, saving $95,000 in the annual budget.

Mar 2022 - Jul 2022

Data Analyst at Mulia Health Dental Care Group

  • ● Conducted comprehensive analysis of customer data across 14 MHDC branches, processing data from over 10,000 customers, resulting in a 15% increase in operational efficiency.
  • ● Produced visually intuitive diagrams and charts using Microsoft Excel, simplifying data interpretation for stakeholders and enhancing decision-making capabilities.
  • ● Delivered data-driven recommendations to stakeholders using Tableau Story, resulting in the implementation of strategic initiatives that led to a 25% increase in company profitability.

Sep 2023 - April 2026

Teaching Assistant (Calculus, Data Science, Probability) — University of Toronto

  • ● Conducted weekly tutorial sessions with 1029 hours of experience for a diverse class of 30+ students, including full responsibility of creating and grading weekly assessments across multiple course sections.
  • ● Held final exam review seminars for classes of over 400+ students, effectively conveying complex course concepts and reinforcing students' understanding of core mathematical, probabilistic, and statistical foundations.
  • ● Played a pivotal role in the rigorous grading process, meticulously assessing assignments, midterms, and the Final Exam for 650+ students, providing in-depth reviews and personalized written feedback.

May 2023 - Dec 2023

Finance & Data Lab Assistant at the University of Toronto

  • ● Developed a Tableau Finance Dashboard showcasing 3 years of Saypo Inc.'s financial performance, leading to enhanced financial transparency and decision-making.
  • ● Created detailed line, bar, and area charts for monthly sales, gross profit, net profit margin, and marketing expenses, improving data accessibility and enabling performance trend monitoring.
  • ● Implemented user-friendly filters for data exploration, allowing users to analyze specific time periods and conduct regional performance comparisons, resulting in more informed decision-making.
  • ● Achieved 98% data completeness by proficiently handling missing values through imputation, ensuring a high-quality dataset for ML model training.
  • ● Enhanced model accuracy from 56% to 83% by selecting various ML models and tuning hyperparameters, improving prediction capabilities.
  • ● Developed a user-friendly loan prediction application, enabling real-time loan approval predictions and enhancing model accessibility.
  • ● Developed and presented an informative Tableau Story on job search strategies in the USA, providing valuable insights into salary trends and job preferences.
  • ● Utilized Best Fit Trend Lines to analyze historical salary growth patterns, aiding users in making informed decisions about their future earning potential.
  • ● Leveraged Tableau Calculated Field to analyze price parity for job destinations, assisting job seekers in optimizing their career choices.
  • ● Utilized Random Forest Classifier to develop an ML model, achieving an outstanding 84.92% accuracy rate on test data, showcasing superior predictive performance.
  • ● Performed extensive data preprocessing, resulting in a remarkable 95% reduction in feature dimensionality, enhancing model accuracy and reducing data complexity.
  • ● Utilized PySpark to process and analyze a Google Play Store dataset with 10,000+ rows, delivering a 10-fold increase in data processing speed compared to Hadoop.
  • ● Conducted in-depth data analysis using PySpark, identifying top-rated apps, most-installed apps, and category-wise installation trends, contributing to strategic decision-making.

Services

Data Analysis

"Unlock insights and drive decisions with my Data Analysis services. From boosting sales efficiency by 70% to enhancing operational performance, I'm your data partner for success. Contact me today!"

Data Engineering

"Elevate your data infrastructure with my Data Engineering expertise. From SQL databases to ETL optimization, I streamline data for actionable insights. Let's power your Database system!"

Data Visualization

"Transform your data into compelling stories with my Data Visualization expertise. From charts to dashboards, I bring insights to life. Let's make your data meaningful!"

Machine Learning

"Unlock the potential of Machine Learning! I offer expert ML services, from predictive modeling to AI solutions. Transform your data into actionable insights with me!"

Business Analysis

"Elevate your business with my Business Analysis services. From optimizing operations to data-driven insights, I've got the solutions. Contact me for transformative results!"

Teaching Assistant

"Elevate your learning experience with my dedicated Teaching Assistant service. Extensive expertise, personalized guidance, and unwavering support to boost your academic success. Let's excel together!"

Portfolio

My Selected Projects :

OpenBrowser-AI

  • ● Built agentic browser automation framework with CodeAgent architecture, raw CDP communication, CLI tooling, and MCP server, supporting 12+ LLM providers, published to PyPI and Claude plugin marketplace.
  • ● Deployed full-stack production system on AWS using Terraform IaC, integrating EC2, CloudFront, S3, ALB, Cognito, RDS, and DynamoDB, with a secure VNC browser locked down via Chromium enterprise policies.
  • ● Built end-to-end SFT and online GRPO reinforcement learning pipelines on Anyscale for autoregressive (Qwen3-8B) and flow matching (ReFusion) models, with QLoRA and KL-penalized policy optimization on multi-GPU clustersBuilt end-to-end SFT and online GRPO reinforcement learning pipelines on Anyscale for autoregressive (Qwen3-8B) and flow matching (ReFusion) models, with QLoRA and KL-penalized policy optimization on multi-GPU clusters

SMART AIR Android App

  • ● Engineered a multi-role Android ecosystem (Child, Parent, Provider) with secure Role-Based Access Control (RBAC), enabling granular, real-time data sharing and privacy management to securely bridge the gap between patients and clinicians.
  • ● Implemented a critical safety algorithm that computes Peak Flow (PEF) zones and evaluates "Red Flag" symptoms, triggering low-latency Firebase Cloud Messaging (FCM) alerts to ensure rapid parental intervention during medical emergencies.
  • ● Developed a gamified medication adherence system and dynamic data visualization dashboard, transforming complex medical logs into exportable PDF/CSV reports to facilitate data-driven consultations and improve patient outcomes.

Maatrx Full Stack Website

  • ● Developed a centralized drug exchange platform to address inefficiency in pharmaceutical supply chains, implementing a real-time matching algorithm using Levenshtein Distance to automate the pairing of hospital drug requests with available surplus inventory.
  • ● Engineered a comprehensive inventory dashboard that integrates the Health Canada Drug Database for precise regulatory compliance, enabling bulk CSV data processing to manage shortages across 13,000+ market products.
  • ● Optimized clinical workflow efficiency by replacing manual communication methods, projected to save clinicians over 15 hours per week and reduce annual drug waste by $12.5 million across the national healthcare network.

Multi AI Agent – Job Seeker

  • ● Developed a multi-agent AI system leveraging CrewAI to analyze job postings, extract key qualifications, and tailor resumes dynamically to maximize candidate alignment with job requirements.
  • ● Engineered a collaborative AI framework integrating tools like SerperDev and MDXSearch, automating personalized resume creation and interview preparation through semantic analysis and data synthesis.
  • ● Designed and implemented a modular AI agent workflow, enabling seamless interaction between research, profiling, and strategic resume crafting agents to enhance job application success rates.

RAG LLM - Chat With Documents and Web

  • ● Engineered advanced RAG solution using LangChain with Chroma Vector Database and HuggingFace Embeddings, enabling efficient, context-aware document retrieval and dynamic LLM responses.
  • ● Integrated multiple LLM providers by seamlessly incorporating OpenAI, Anthropic, and Groq APIs into unified framework, optimizing performance and scalability across diverse conversational AI applications.
  • ● Developed interactive Streamlit application that leverages real-time, streaming chat and RAG-powered document search, significantly enhancing user engagement and accessibility to critical information.

Multimodal LLM - Chat With Image

  • ● Engineered multimodal LLM using the IBM WatsonX API and Streamlit to develop a “chat with image” interface, seamlessly integrating real-time image processing with interactive text conversations.
  • ● Integrated the open source llama 3.2 90b vision instruct model to enhance the assistant’s multi-modal understanding, delivering precise, context-aware responses to both visual and textual inputs.
  • ● Optimized secure communication and user experience by implementing advanced authentication and dynamic Streamlit features, including customizable dark mode support, and chat history downloads.

AI Agent - Research Assistant

  • ● Pioneered AI Agent Assistant leveraging CrewAI Framework and Exa API for enriched topic analysis, integrating OpenAI, Groq, and Ollama models to deliver robust, multi-faceted research insights.
  • ● Engineered seamless API integrations that enabled rapid switching between OpenAI, GROQ, and Ollama models, optimizing secure key management and real-time analytics via dynamic API orchestration.
  • ● Developed interactive Streamlit interface that unified advanced AI Agent capabilities with powerful LLM APIs, streamlining research workflows and delivering visually engaging, comprehensive reports.

Deep Reinforcement Learning – Space Invaders

  • ● Designed and implemented Deep Q-Network (DQN) using TensorFlow, integrating dueling network architecture and epsilon-greedy policy for efficient decision-making in complex environments.
  • ● Achieved enhanced performance in reinforcement learning by constructing convolutional neural network (CNN) optimized for visual input from Atari games using the OpenAI Gym environment.
  • ● Conducted extensive testing of Deep Reinforcement Learning agents, leveraging pre-trained weights and achieving consistent improvements in episodic reward metrics across multiple simulations.

DCGAN Face Generator

  • ● Implemented DCGAN with PyTorch to generate realistic faces, training the model on a dataset of 21,551 manually resized face images (64x64 pixels) for optimal performance.
  • ● Designed and implemented a well-balanced Discriminator Neural Network with 2.7 million parameters and a Generator Neural Network with 3.8 million trainable parameters.
  • ● Developed a comprehensive approach for efficient data preprocessing, including resizing and batch normalization, coupled with GPU acceleration (CUDA) for rapid training performance.

Deep Learning: Human Video Activity Recognition

  • ● Implemented a Deep Learning Human Activity Recognition system using a hybrid CNN and LSTM architecture, resulting in accuracy by 91% on the testing dataset.
  • ● Developed the preprocessing pipeline by implementing normalization and frame extraction, resulting in a 25% reduction in overfitting and enhancing the model generalizability.
  • ● Implemented a LRCN architecture, seamlessly integrating spatial and temporal features, demonstrating a deep understanding of computer vision and sequential data processing.

Deep Learning: Image Caption Generator

  • ● Implemented a customized bidirectional LSTM with attention mechanisms and tokenization for text analysis, achieving a BLEU score of 0.54, showcasing advanced NLP concepts.
  • ● Utilized transfer learning with pre-trained VGG16 for effective image features extraction, showcasing expertise in integrating diverse neural networks for superior performance.
  • ● Successfully integrated image processing techniques, encompassing extracting, loading, and preprocessing, to demonstrate a comprehensive approach to images data handling.

Deep Learning: Handwritten Digit Recognition

  • ● Trained a convolutional neural network (CNN) model to recognize handwritten digits using the MNIST handwritten digit dataset, achieving a high accuracy of 98% on the test dataset.
  • ● Significantly accelerated model training by implementing GPU (CUDA) utilization, harnessing parallel processing to achieve a 3x reduction in training time for deep learning models.
  • ● Processed and analyzed 70,000 handwritten digit images with PyTorch, including data loading and transformation, showcasing strong skills in handling large datasets.

Deep Learning: Image Classification

  • ● Developed a machine learning model using TensorFlow and Keras, achieving significant accuracy improvements from 56% to 84%, in a dataset consisting of 60,000 color images.
  • ● Employed convolutional neural network (CNN) with batch normalization, dropout, and various convolution layers, resulting in a deep learning model with 2,397,226 parameters.
  • ● Analyzed and presented results through visualizations, including classification report and confusion matrix, demonstrating strong data analysis and reporting skills.

Deep Learning: Speech Emotion Recognition

  • ● Trained and implemented an LSTM neural network architecture with 77,160 trainable parameters, achieving outstanding accuracy of 98.61% on the testing dataset.
  • ● Engineered a robust data preprocessing pipeline, including the function, extract_mfcc, to calculate Mel-frequency cepstral coefficients (MFCCs) of audio files from librosa audio library.
  • ● Innovatively integrated a user-friendly Streamlit version, enabling one-click emotion recognition for users, enhancing accessibility to the developed SER model.

Loan Prediction Machine Learning Model

  • ● Achieved 98% data completeness by proficiently handling missing values in critical columns through imputation using NumPy and Pandas, ensuring a pristine dataset for ML model training.
  • ● Enhanced model accuracy from 56% to 83% by meticulously selecting various ML models from Scikit-learn and tuning the hyperparameter, through data-driven strategies.
  • ● Developed a user-friendly loan prediction application, facilitating real-time loan approval predictions for users and enhancing model accessibility and usability.parisons, resulting in more informed decision-making.

Income Prediction ML Random Forest Model

  • ● Utilized Random Forest Classifier to develop an ML model, yielding an outstanding 84.92% accuracy rate on the test data, showcasing superior predictive performance.
  • ● Performed extensive data preprocessing, encompassing One-hot Encoding for multi-class features, resulting in a remarkable 95% reduction in feature dimensionality.
  • ● Leveraged correlation analysis and feature importance to pinpoint the top 5% of critical features among 90+ columns, enhancing accuracy score and reducing data complexity by 75%.

Tableau Finance Profit & Loss Dashboard

  • ● Developed a Tableau Finance Dashboard, showcasing Saypo Inc.'s 3 years financial performance, featuring interactive visualizations of Profit and Loss Statements, Sales, and Profit Margins.
  • ● Created detailed line, bar, and area charts to illustrate monthly Sales, Gross Profit, Net Profit Margin, and Marketing Expenses, enabling users to monitor performance trends effectively.
  • ● Implemented user-friendly filters for data exploration, allowing users to analyze specific time periods and conduct regional performance comparisons on the dashboard.

Podcast Summarizer Project

  • ● Achieved reliable retrieval of podcast episode details and audio transcription through efficient use of HTTP requests and headers, enhancing the overall performance of the Podcast Summarizer.
  • ● Engineered an intuitive user interface for the Podcast Summarizer using Streamlit, enabling users to easily input episode IDs and download episode summaries with a single click.
  • ● Led the initiative to develop a resilient API communication system, streamlining interactions with both AssemblyAI and Listen Notes APIs to achieve seamless integration.

Kimia Farma Sales Dashboard Replica

  • ● Engineered a SQL database with 140,000+ entries and 30+ columns, optimizing access across 20+ branches, resulting in a remarkable 70% boost in sales distribution efficiency.
  • ● Leveraged SQL querying expertise to optimize data ETL, leading to a 33% reduction in data processing time, and directly contributed to a 40% reduction in operational cost.
  • ● Designed and developed a Tableau dashboard for sales data, enhancing data accessibility and facilitating data-driven decision-making, saving $95,000 in the annual budget.

Database Driven Web Application

  • ● Implemented a secure Flask web application with SQLAlchemy, ensuring data confidentiality through a secret key and SQLite database encryption.
  • ● Facilitated seamless user interaction by developing dynamic web routes, allowing users to perform Create, Read, Update, and Delete (CRUD) operations on tasks.
  • ● Elevated the user experience by incorporating Bootstrap for a responsive design and Animate.css for modern animation effects, resulting in an engaging Task Manager application.

Tableau Story: Job Search Strategy

  • ● Developed and presented an informative Tableau Story titled "Searching For a New Job in USA," providing valuable insights into salary trends, VISA class impact, and job preferences.
  • ● Utilized Best Fit Trend Lines to analyze historical salary growth patterns, aiding users in making informed decisions about their future earning potential.
  • ● Leveraged Tableau Calculated Field to analyze price parity to identify the most financially advantageous job destination, helping job seekers optimize their career choices.

Data Analysis of Google Play Store Applications Using PySpark

  • ● Utilized PySpark to effectively process and analyze a Google Play Store dataset with 10,000+ rows, delivering a 10-fold increase in data processing speed compared to Hadoop.
  • ● Conducted in-depth data analysis using PySpark, identifying top-rated apps, most-installed apps, and category-wise installation trends, contributing to strategic decision-making.

Bikeshare Data Analysis in Toronto Using R Programming Language

  • ● Developed data analysis skills through analyzing and visualizing bikeshare data for the Greater Toronto Area (from open.toronto.ca) using R programming language.
  • ● Conducted exploratory data analysis by creating tables and graphs to identify trends in bikeshare usage, informing business decisions for bikeshare companies and city officials.
  • ● Demonstrated proficiency in data wrangling and cleaning, including handling missing data, transforming data types, and merging datasets to create a comprehensive analysis.

Folium Toronto Apartment Evaluation

  • ● Created a comprehensive analysis of apartment building evaluations, achieving a 98% data completeness rate by proficiently managing missing data with Pandas and NumPy.
  • ● Developed an interactive Folium map displaying apartment evaluation scores categorized into five distinct classes with unique marker colors, accompanied by a custom legend.
  • ● Identified spatial clusters of high and low-quality apartment buildings in diverse Toronto regions, providing critical insights for urban planning and policy formulation.

Contact Me

Have You Any Questions ?

I'M AT YOUR SERVICES

Call Me On

+14167317583

Office

Toronto, Ontario, Canada

Email

billy.suharno@gmail.com

Website

https://billy-enrizky.github.io/portfolio/

SEND ME AN EMAIL

I'M VERY RESPOSIVE TO MESSAGES