Shivani Kanodia

Associate Consultant

San Francisco, California, United States7 yrs 3 mos experience

AI EnabledAI ML Practitioner

Key Highlights

Developed AI-driven pipelines for recruitment.
Achieved 76% accuracy in fraud detection.
Improved content engagement by 120% at Akamai.

Stackforce AI infers this person is a Data Science and Analytics professional with a focus on Machine Learning and Business Intelligence.

Contact

kanodiashivani27@gmail.com LinkedIn

Skills

Core Skills

Machine LearningData ScienceData VisualizationAnalytics

Other Skills

API CALLSAgile Project ManagementAnalytical SkillsBusiness StrategyCommunicationCross-EncoderDashboard BuildingData WranglingEDAExploratory Data AnalysisFlaskGoogle Data StudioJupyterLLMLLaMA

About

Professional with 5 years of overall experience, currently specializing in People Analytics and transitioning into Data Science through a master’s focused on End to End ML, Python, MLFLOW, RAG's and LLMs. Programming & Analytics: Python, (Pandas, NumPy, Scikit-learn, SpaCy, TensorFlow, Hugging Face, OpenAI) Databases: SQL Server, MySQL Machine Learning & Deep Learning: Random Forest, XGBoost, Clustering, NLP, LLM's Cloud & MLOps: AWS (Elastic Beanstalk and S3), MLflow, Delta Lakes Other Tools: Tableau, Gurobi, GitHub, VS Code, Copilot. Soft Skills: Communication, Stakeholder Management, Data Storytelling, Cross-functional Collaboration. Github Link: https://github.com/Shivanikanodia

Experience

7 yrs 3 mos

Total Experience

1 yr 9 mos

Average Tenure

1 yr 10 mos

Current Experience

California state university - east bay

Business Analytics Graduate

Aug 2024 – Present · 1 yr 10 mos · Hayward, California, United States

RAG-AI Agent:
Developed an AI-driven pipeline using RAG, Bi-encoder + cross-encoder models for semantic retrieval and Databricks Llama-4 LLM for recruiter-ready resume summaries.
Built evaluation metrics for relevance, latency, and accuracy, automated candidate comparison, and optimized inference via model caching and reranking.
Tools & Technologies: Python, Sentence Transformers, Cross-Encoder, LLM,, Semantic Search
Credit Card Fraud Detection Application:
Built and deployed an end-to-end fraud detection system using XGBoost and a Flask REST API for real-time transaction risk scoring.
Engineered risk-based features (amount patterns, time-of-day trends, merchant fraud rates) and applied SHAP explainability for model transparency.
Achieved 76% accuracy and 70% recall, detecting 72 of 100 frauds, with a reproducible ML pipeline managed via Git.
Tools & Technologies: Python, Flask, Scikit-learn, XGBoost, Pandas, SHAP

PythonSentence TransformersCross-EncoderLLMSemantic SearchXGBoost+6

Databricks

People Analytics

Feb 2024 – Jul 2024 · 5 mos · Bengaluru, Karnataka, India

People's Team

Akamai technologies

Consultant

Sep 2021 – Dec 2023 · 2 yrs 3 mos · Bangalore Urban, Karnataka, India

Data Visualization: Developed centralized dashboards for to automate reporting and visualization, improving data clarity and saving ~40 hours/month.
Performed exploratory data analysis on LinkedIn engagement data (Impressions, CTR, Unique visitors) using Tableau to identify high-performing content categories and underrepresented job function.
Delivered actionable insights that optimized Akamai India’s content mix and audience targeting, leading to a 120% increase in page traffic, 69% rise in unique visitors in 2 months and improved ranking from 6th to 4th among competitors.

TableauData VisualizationExploratory Data AnalysisAnalytics

Dexian

Business Analyst

Aug 2018 – May 2021 · 2 yrs 9 mos · Chennai, Tamil Nadu, India

Enhanced operational efficiency through process gap mapping, documentation, and the implementation of best practices.
Collaborated with cross-functional teams to clarify business requirements, develop work breakdown structures, and improve data consistency across HR processes.
Analyzed quarterly objectives and over 100+ staffing requirements to successfully deliver resources while minimizing cost and improving profit margins.