SOUMYA SAFALLYA SAHOO

About

Computer Science and Engineering student at Odisha University of Technology & Research with experience in machine learning and data analytics internships. Built projects in fraud detection, operational analytics, and voice assistants using Python, SQL, and common data/ML tools.

Experience

• ML Intern
  IIT Bhubaneswar

  Analysed large-scale gait datasets to improve data reliability for machine learning and computer vision applications. Worked with Vision-Language Models (LLaVA) for multimodal analysis, feature extraction, and gait recognition tasks. Conducted exploratory data analysis, annotation validation, and model evaluation to support the GaitPar project.

• Data Analytics Intern
  IBM SkillsBuild

  Completed a 6-week Data Analytics internship under the IBM SkillsBuild Summer Internship Program. Worked with Python, Pandas, NumPy and data visualization techniques for analyzing and interpreting datasets. Applied data preprocessing, exploratory analysis, and visualization techniques to derive meaningful insights from data.

Education

• Bachelor of Technology
  Odisha University of Technology & Research
  Computer Science and Engineering · 2023 – 2027

Skills

• SQL <3 months
• C <3 months
• Computer Networks <3 months
• Computer Vision <3 months
• Data Analysis 6 to 12 months
• Data Preprocessing 6 to 12 months
• Data Structures <3 months
• Data Visualization 6 to 12 months
• Python <3 months
• Machine Learning <3 months
• DNS <3 months
• OSI Model <3 months
• Exploratory Data Analysis 6 to 12 months
• Data Handling 6 to 12 months
• VLAN <3 months
• TCP/IP <3 months
• DHCP <3 months
• Routing and Switching <3 months
• NAT <3 months
• Oop <3 months
• Ethernet <3 months
• Patent Law <3 months
• Advanced DBMS <3 months

Tools / apps / platforms

• Git <3 months
• GitHub <3 months
• Google Colab <3 months
• Microsoft Excel <3 months
• Microsoft Power BI <3 months
• VS Code <3 months

Projects

• Sonix
  Python, FastAPI, AssemblyAI, HTML, CSS, gTTS

  Built a real-time AI voice assistant with speech-to-text and NLP-based response generation using a scalable FastAPI web application with an intuitive UI.

• Customer Operations Analytics Dashboard Repository
  Python, Pandas, SQL, Excel, Power BI

  Analyzed multi-source operational data to identify trends and bottlenecks. Performed data cleaning, validation, and exploratory analysis on inconsistent and missing records, and built interactive Power BI dashboards to track operational KPIs.

• Fraud Detection Repository
  Python, Pandas, NumPy, Scikit-learn, XGBoost, Matplotlib, Seaborn

  Built a machine-learning fraud detection system using Logistic Regression, Random Forest, XGBoost, and Neural Networks with class imbalance handling. Selected the best model based on F1-score and ROC-AUC, achieving strong fraud detection performance on unseen data.

Courses & certifications

• Apply AI
• Introduction to Modern AI
• IBM Data Analytics
• Python Essentials 2
• Python Essentials 1
• CCNA-3
• CCNA-2
• CCNA-1

⚽ Extracurricular activities

• Debates and Presentations

  Demonstrated strong communication and public-speaking skills through active participation in debates and presentations.

• Core Member, Zairza

  Core member of Zairza.

🤝 Volunteering

• Red Cross · Volunteer

  Assisted in humanitarian and community service initiatives.

🎯 Hobbies & interests

• Badminton
• debate