Skip to content
View 47096's full-sized avatar
🏠
Working from home
🏠
Working from home
1 follower · 3 following

Achievements

Achievement: QuickdrawAchievement: Pair Extraordinairex2Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pair Extraordinairex2Achievement: Pull Sharkx2Achievement: YOLO

Block or report 47096

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
47096/README.md

Hey, I'm Sam 👋

You know how everyone talks about "data-driven decisions" but nobody actually knows where to start? So what I do is build tools that bridge that gap — from customer churn prediction models to AI-powered analytics. In fact, I've spent 10+ years in customer analytics and now build the AI tools I wish I had back then.

🛠️ Stack: AI: Claude Code, MiMo Desktop, Hermes Agent Desktop, Codex | Data: Python, R, SQL | Infra: Firebase, Render, Supabase, Vercel

💼 Consulting: Founder at datafying, helping businesses with customer analytics (churn prediction, segmentation) and turning data into decisions that elevate customer experience

👨‍🏫 Mentoring: 20+ emerging data professionals to become strategic business partners who drive decisions with data

🔨 Currently: AI voice & music tools, plus agentic workflows for customer analytics

Selected work

Ship it live

App What it is Demo
hum AI music generator — chat, docs, repos, or YouTube → songs live
hanna Chrome TTS extension — karaoke highlighting, voice design & clone repo
mimo-storyteller Multi-character audio stories with karaoke playback live
mimo-reader Browser TTS — 100+ voices, design & clone, export WAV/MP3 live
puff Quit-smoking PWA — hold + blow, streaks, Firebase sync live
noise-monitor PWA noise monitor — live waveform + spoken alerts live

Customer analytics & data science

R · Python · SQL — churn, marketing response, VoC, model explainability

Work Business question
tidymodels Who will churn? — Tree vs RF vs XGBoost
predict-marketing-response-with-xgboost Who will respond to a campaign?
linear-regression-in-r Where should ad spend go?
review-data-using-SVC What are customers saying? (review NLP)
model-studio Why did the model decide that? (explainability)
persona Synthetic customer interviews in 15 mins

More ML/stats notebooks (Prophet, AutoKeras, GLM, …) — repos

Teaching

Case studies

Pinned Loading

  1. mimo-storyteller mimo-storyteller Public

    Multi-character TTS audio story app — paste a story, assign voices, listen to AI narration with karaoke highlighting

    JavaScript 1

  2. mimo-reader mimo-reader Public

    Design custom voices, clone any voice from audio, and generate natural speech — all in your browser. 100+ presets across 6 categories. Export WAV/MP3. Great for podcasts, e-learning, and marketing …

    HTML

  3. persona persona Public

    Generate customer personas and interview them in 15 minutes instead of 2 weeks. Claude Code skill that creates synthetic personas, simulates structured interviews, and produces actionable reports w…

  4. lux-tts lux-tts Public

    Voice cloning in Google Colab — clone any voice from a short audio sample and generate speech, no GPU setup required

    1

  5. how-to-spell how-to-spell Public

    "How do you spell dinosaur?" — now your kid can just ask the app on an older phone or your phone. Voice-powered spelling helper for children with real-time waveform feedback and fuzzy content filte…

    HTML

  6. puff puff Public

    A progressive web app that helps you quit smoking by simulating the cigarette experience — track cravings, build streaks, and see your savings grow.

    JavaScript