Post Job Free
Sign in

Generative AI & Time Series Analytics Student

Location:
Hyderabad, Telangana, India
Posted:
November 03, 2026

Contact this candidate

Resume:

RAMAVATH GANESH

Hyderabad, Telangana, India — +91-910******* — *****************@*****.***

GitHub — LinkedIn

SUMMARY

M.Sc. Statistics student with a strong foundation in Python, SQL, statistical analysis, machine learning, and time series

forecasting. Hands-on experience developing Generative AI applications using LLMs, RAG, LangChain, and multi-agent

systems, along with predictive modeling and data analysis projects.

EDUCATION

Master of Science (M.Sc.) in Statistics 2024 – 2026

Banaras Hindu University (BHU), Varanasi, India CGPA: 7.0 / 10

Bachelor of Science (B.Sc.) in Mathematics, Physics, Statistics 2020 – 2023

Osmania University, Hyderabad, India CGPA: 7.44 / 10

TECHNICAL SKILLS

• Programming Languages: Python, SQL

• Generative AI & LLMs: LLMs, RAG, LangChain, Multi-Agent Systems, Vector Databases, Function Calling

• Machine Learning & Deep Learning: Regression, Classification, Predictive Modeling, Model Evaluation, Cross-

Validation, LSTM

• Time Series Forecasting: ARIMA, SARIMA, SARIMAX, ACF/PACF Analysis, Seasonal Decomposition

• Data Analysis & Visualization: Data Cleaning, EDA, Statistical Analysis, Matplotlib, Seaborn

• Python Libraries: Pandas, NumPy, Scikit-Learn, Statsmodels, BeautifulSoup, Cloudscraper, Requests

PROJECTS

Multi-Agent AI Research System 2026

Technologies: Python, LangChain, Google Gemini API, Tavily API, Requests, BeautifulSoup

• Developed a multi-agent AI research system using Python, LangChain, and Google Gemini API, with specialized

Search and Reader agents, followed by Writer and Critic chains.

• Integrated Tavily Web Search to retrieve recent online information and built a custom web-scraping tool using Requests

and BeautifulSoup to extract detailed content from selected sources.

• Built an automated research pipeline that processes a user-defined topic through web search, URL selection, content

extraction, and LLM-based report generation with key findings, conclusions, and source references.

• Implemented a Critic Chain using Gemini to evaluate generated reports, identify strengths and areas for improvement,

and provide structured feedback on the research output.

Solar Radiation Forecasting and Weather Impact Analysis 2025 – 2026

Supervised by Prof. Sanjeev Kumar, Department of Statistics, Banaras Hindu University (BHU)

• Developed a solar radiation forecasting framework using 26+ years of daily meteorological data (1979–2024) from

Telangana to support renewable energy planning.

• Performed time series analysis, including ADF testing, seasonal decomposition, differencing, and ACF/PACF analysis

to identify model parameters.

• Built and compared SARIMA, SARIMAX, and LSTM models for solar radiation forecasting, incorporating tempera-

ture, cloud cover, dew point, and UTCI as exogenous weather predictors.

• Evaluated forecasting performance using MAE and RMSE, with SARIMAX achieving lower error than baseline

SARIMA and LSTM models.

• Generated 12-month ahead forecasts and analyzed the relationship between weather conditions and solar energy

generation for long-term planning.

Insurance Cost Estimation and Risk Analysis 2025

Technologies: Python, Scikit-Learn, Pandas, NumPy, Matplotlib, Seaborn

• Developed a predictive machine learning solution to estimate medical insurance costs based on demographic and

lifestyle factors.

• Conducted Exploratory Data Analysis (EDA), data preprocessing, and feature engineering to identify key cost drivers.

• Built and compared Linear Regression, Decision Tree, Random Forest, and Gradient Boosting models for insurance

cost prediction.

• Achieved optimal performance with Gradient Boosting (R = 0.86), identifying age, BMI, and smoking status as

primary drivers affecting insurance charges.

CERTIFICATIONS

• IBM Machine Learning with Python – Coursera (2025)

• Data Analytics with Python – NPTEL (2025)

• Introduction to Biostatistics – NPTEL (2025)



Contact this candidate