╔══════════════════════════════════════════════════════════════════════════════════╗
║                                                                                  ║
║   $ whoami                                                                       ║
║   > ashwin.pillanda.ravindra                                                     ║
║   > data_scientist @ tata_consultancy_services                                   ║
║   > shipping production ML for fortune_500 clients                               ║
║   > GRE: 339/340                                                                 ║
║                                                                                  ║
╚══════════════════════════════════════════════════════════════════════════════════╝

---

> cat ./about.md

class Ashwin:
    """Data Scientist & Analytics Engineer @ TCS"""
    
    def __init__(self):
        self.role       = "Data Scientist & Analytics Engineer"
        self.company    = "Tata Consultancy Services (TCS)"
        self.clients    = ["Stellantis NV", "Samsung", "Bosch", "KPMG"]
        self.location   = "Bengaluru, India"
        self.gre        = {"total": 339, "quant": 169, "verbal": 170}  # /340
        
    def current_mission(self):
        return {
            "building":  "Predictive supply chain models on Azure",
            "designing": "Executive-grade BI dashboards (Power BI + Fabric)",
            "shipping":  "Scalable ETL with ADF + Snowflake",
            "next":      "Grad school — Fall 2026 (Analytics / MIS)"
        }
    
    def philosophy(self):
        return "I choose tools that ship production results at scale — not resume decorations."

---

> systemctl status production-impact.service

● production-impact.service — Enterprise Delivery Pipeline (2021–2025)
  Status: ██████████████████████████████████ ACTIVE
  Uptime: 4 years | Clients: Fortune 500 | NDAs: Enforced

📦 supply_chain_optimization client: Stellantis NV system: Real-time Power BI + Azure SQL scope: Global logistics monitoring impact: ~20% reduction in logistics overhead	📈 demand_forecasting client: Samsung & Bosch models: Random Forest, Gradient Boosting horizon: 4–6 week inventory prediction impact: 15–20% forecast accuracy uplift
🔄 customer_retention client: Multi-Client model: Decision tree churn predictor strategy: Targeted intervention pipeline impact: 20% churn rate reduction	☁️ cloud_migration_etl client: Multi-Client stack: Azure Data Factory pipelines scope: Legacy on-prem → cloud migration impact: 30% faster | 99.9% uptime

🏆 × 6  "Star of the Month" — TCS  |  Delivery Excellence & Client Impact

---

> cat /etc/tech-stack.conf

┌──────────────────────────────┬────────────────────────────────────────┐
│ DATA SCIENCE & ML            │ BUSINESS INTELLIGENCE                  │
│ ─────────────────            │ ─────────────────────                  │
│ Python ◆ Pandas ◆ NumPy      │ Power BI ◆ Tableau ◆ Qlik              │
│ Scikit-learn ◆ TensorFlow    │ DAX ◆ Advanced Excel                   │
│ XGBoost ◆ Random Forest      │                                        │
│ R                            │                                        │
├──────────────────────────────┼────────────────────────────────────────┤
│ DATA ENGINEERING             │ CLOUD & DEVOPS                         │
│ ────────────────             │ ──────────────                         │
│ Azure Data Factory           │ Azure Ecosystem                        │
│ PySpark ◆ Snowflake          │ Git                                    │
│ BigQuery ◆ SQL Server        │                                        │
│ Microsoft Fabric             │                                        │
│ Azure Synapse Analytics      │                                        │
└──────────────────────────────┴────────────────────────────────────────┘

---

> ls -la ./projects/

drwxr-xr-x  ashwin/projects
│
├── 🔊 audio-signal-enhancement/
│   ├── desc:    Denoising autoencoder (TensorFlow/Keras) — IISc internship
│   ├── result:  +11.7 dB SNR improvement over baseline
│   └── stack:   [TensorFlow, Keras, Librosa]
│
├── 🏥 healthcare-diagnostic-hub/
│   ├── desc:    Ensemble ML for diabetes & cancer risk prediction
│   ├── result:  +21% accuracy via SMOTE + feature engineering
│   └── stack:   [Scikit-learn, SMOTE, Explainable AI]
│
└── 🛡️ network-security-analytics/
    ├── desc:    CNN intrusion detection on NSL-KDD dataset
    ├── result:  98% attack classification accuracy
    └── stack:   [TensorFlow, Keras]

---

> cat ./certifications.log

+ [2025]  Microsoft Certified: Fabric Analytics Engineer Associate
+ [2024]  Microsoft Certified: Power BI Data Analyst Associate
+ [2024]  PCEP — Certified Entry-Level Python Programmer
+ [2023]  Microsoft Certified: Power Platform Developer Associate

---

> neofetch --github

 

---

> echo $CONTACT

┌──────────────────────────────────────────────────────────────┐
│                                                              │
│   > Interested in data science, cloud infra, or BI?          │
│   > Let's build something that ships.                        │
│                                                              │
│   💼 linkedin.com/in/prashwin                                │
│   📧 ashwinpravindra@gmail.com                               │
│                                                              │
└──────────────────────────────────────────────────────────────┘