Skip to content
View AkashMs24's full-sized avatar
🏠
Working from home
🏠
Working from home

Highlights

  • Pro

Block or report AkashMs24

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.

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
AkashMs24/README.md

Typing SVG


LinkedIn  Portfolio  Gmail  GitHub




🏆 RECOGNITION & RESEARCH

🥈 2nd Prize — IdeaThon  |  MedVerify: AI-powered Medical Certificate Fraud Detection Presidency University · 2026
🌟 Special Recognition — Social Impact  |  FusionX Hackathon 2026
📄 Research Accepted — ICDAI 2026  |  Explainable ML for Employee Attrition Prediction Int'l Conference · 2026
📄 Research Accepted — CoMSYS 2026  |  XAI Systems Int'l Conference · 2026



🧠 WHO AM I?

#!/usr/bin/env python3
# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

class AkashMS:
    name        = "Akash M S"
    role        = "ML Engineer · Explainable AI Specialist · Full-Stack AI Builder"
    university  = "Presidency University, Bengaluru · B.Tech CSE — Data Science · 2026"
    status      = "🟢 Actively seeking Full-time roles in ML / Data Science / AI"

    awards = [
        "🥈  IdeaThon 2nd Prize  →  MedVerify (Medical AI Fraud Detection)  · 2026",
        "🌟  FusionX Special Recognition  →  Social Impact Category  · 2026",
        "📄  ICDAI 2026 Accepted  →  Explainable ML for HR Attrition",
        "📄  CoMSYS 2026 Accepted  →  XAI Systems Research",
    ]

    what_i_build = [
        "🛡️  XAI systems where every prediction comes with a reason",
        "🔍  Fraud & risk engines deployed in production (not just notebooks)",
        "🤖  LLM-powered apps with real API integrations",
        "📊  End-to-end ML pipelines: data → model → deploy → explain",
    ]

    superpowers = {
        "core"     : ["Explainable AI (SHAP/LIME)", "Production ML", "LLM Engineering"],
        "domains"  : ["Fraud & Risk", "HR Analytics", "AgriTech AI", "Healthcare AI", "NLP"],
        "mantra"   : "A prediction without an explanation is just a confident guess.",
    }

# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━



🚀 What I've Actually Shipped


# Project What It Solves Stack Live
🥈 MedVerify IdeaThon 2nd Prize Detects forged medical certificates using AI — built for a real institutional pain point Gemini API JS AI
📄 Employee Attrition XAI ICDAI 2026 Tells HR not just who will quit — but exactly why, with SHAP-driven action plans Random Forest SHAP Python
🧠 XAI Copilot Explainable loan credit risk — SHAP decisions, bias detection & LLM copilot in one app FastAPI React SHAP LLM
🛡️ Fraud Detection System Cost-sensitive real-time fraud scoring — optimizes for business loss, not just accuracy XGBoost SHAP FastAPI
🔍 SCAMGUARD AI Detects fake job postings via NLP + ML with transparent risk scores & explainability NLP scikit-learn Streamlit
🎙️ SpeechFlow Production-grade live speech-to-text with real WebSocket architecture & sub-second latency Groq Whisper WebSockets JS
📋 CollabBoard Real-time multi-user Kanban with live sync, AI suggestions & full PostgreSQL backend Node.js Socket.io PostgreSQL
📊 DecisionIQ BI LLM + ML for forecasting, anomaly detection & business intelligence in one platform LLM XGBoost Streamlit
🌾 KrishiAI / FarmVoice Multilingual voice-powered crop advisory for Indian farmers using Claude API Claude API NLP Voice
🎯 Recommendation Engine Domain-agnostic, cold-start ready semantic recommender with full explainability TF-IDF NLP Streamlit
📈 A/B Testing Analysis Statistical evaluation of conversion uplift with hypothesis testing & confidence intervals Python Statistics Jupyter



⚡ Tech Stack


Languages   Python JavaScript SQL R C


ML / AI / XAI   scikit-learn XGBoost TensorFlow PyTorch SHAP LangChain HuggingFace


LLM / APIs   Claude Gemini Groq OpenAI


Backend & Deploy   FastAPI Node.js Django Streamlit Docker Vercel AWS


Data & Viz   Pandas NumPy Plotly Power BI PostgreSQL MongoDB




📊 GitHub Activity


Ashutosh's github activity graph

GitHub Streak
GitHub Trophies

Visitor Count  GitHub followers




🎯 What I Stand For

╔══════════════════════════════════════════════════════════════════════╗
║                                                                      ║
║   "A prediction without explanation is just a confident guess."      ║
║                                                                      ║
║   "I don't train models. I build systems that justify decisions."    ║
║                                                                      ║
║   "Every dataset has a truth buried in it.                           ║
║    My job is to make the model prove it."                            ║
║                                                                      ║
╚══════════════════════════════════════════════════════════════════════╝



🌐 Currently Open To

╔══════════════════════════════════════════════════════════════════════╗
║                                                                      ║
║   🎯  Full-time · Data Science / ML Engineering / AI                ║
║                                                                      ║
║   📄  Research collaborations & open-source contributions           ║
║                                                                      ║
║   💡  Problems that need AI with accountability built in            ║
║                                                                      ║
║   🌍  Remote & on-site · Bengaluru and beyond                       ║
║                                                                      ║
║   ─────────────────────────────────────────────────────────         ║
║                                                                      ║
║   Core domains:                                                      ║
║   Explainable AI  ·  Fraud & Risk  ·  NLP  ·  LLM Engineering       ║
║   Healthcare AI   ·  AgriTech      ·  HR Analytics                  ║
║                                                                      ║
╚══════════════════════════════════════════════════════════════════════╝

LinkedIn  Email  Portfolio



Pinned Loading

  1. Cost-Sensitive-Real-Time-Fraud-Detection-Decision-System Cost-Sensitive-Real-Time-Fraud-Detection-Decision-System Public

    End-to-end fraud detection decision system with cost-sensitive ML, explainability, and real-time API deployment.

    Python 1

  2. Decisioniq-ai-business-intelligence Decisioniq-ai-business-intelligence Public

    AI-powered decision intelligence system using ML + LLM to forecast trends, detect anomalies, and generate actionable business insights.

    Python

  3. JeevanMitraAI JeevanMitraAI Public

    🌿 JeevanMitra AI – Smart Farming Companion HACKATHON SPECIAL RECOGNITION

    JavaScript

  4. collabboard collabboard Public

    CollabBoard 📋 is a full-stack, production-grade collaborative task management platform. Multiple users can work on the same Kanban board simultaneously — tasks move, update, and appear in real time…

    JavaScript

  5. speechflow speechflow Public

    Production-grade Speech-to-Text powered by Groq Whisper API 🎙️

    JavaScript

  6. medverify medverify Public

    Medical Certificate Fraud Detection - IdeaThon 2nd Prize

    JavaScript