Patel Jal

Data Scientist

Vadodara, Gujarat 1+ yrs exp 83 · Excellent

About

Results-driven Data Scientist with 1.5+ years of combined internship experience in end-to-end machine learning, data analysis, and AI-powered solutions. Proficient in building supervised classification models, EDA pipelines, SQL databases, and interactive dashboards. Currently deepening expertise in Data Science with AI at Labmentix. Proven ability to translate complex data into actionable business insights with clean, reproducible code. Committed team player with a strong foundation in statistics, Python, and modern ML workflows.

Skills & Expertise (29)

Jupyter Notebook Advanced

8.5/10

1.5

Years Exp

Pandas Advanced

8.5/10

1.5

Years Exp

NumPy Advanced

8.5/10

1.5

Years Exp

scikit-learn Advanced

8.5/10

1.5

Years Exp

Python Advanced

8.2/10

1.5

Years Exp

Google Colab Advanced

8.0/10

1.5

Years Exp

GitHub Advanced

8.0/10

1.5

Years Exp

Git Advanced

8.0/10

1.5

Years Exp

Data Cleaning Advanced

8.0/10

1.5

Years Exp

Feature Engineering Advanced

8.0/10

1.5

Years Exp

Seaborn Advanced

8.0/10

1.5

Years Exp

Matplotlib Advanced

8.0/10

1.5

Years Exp

SQL Intermediate

7.5/10

1.5

Years Exp

MySql Intermediate

7.5/10

1.5

Years Exp

Streamlit Intermediate

7.5/10

1.5

Years Exp

Statistical Analysis Intermediate

7.5/10

1.5

Years Exp

Hyperparameter Tuning Intermediate

7.5/10

1.5

Years Exp

ETL Pipelines Intermediate

7.0/10

1.5

Years Exp

Accuracy Intermediate

7.0/10

1.5

Years Exp

Confusion Matrix Intermediate

7.0/10

1.5

Years Exp

ROC-AUC Intermediate

7.0/10

1.5

Years Exp

Precision Intermediate

7.0/10

1.5

Years Exp

Recall Intermediate

7.0/10

1.5

Years Exp

F1-Score Intermediate

7.0/10

1.5

Years Exp

Feature Selection Intermediate

7.0/10

1.5

Years Exp

Decision Tree Intermediate

7.0/10

1.5

Years Exp

Logistic Regression Intermediate

7.0/10

1.5

Years Exp

MS Excel Intermediate

7.0/10

1.5

Years Exp

EDA

Work Experience

Data Science with AI Intern

Labmentix

Mar 2026 - Present

Building and deploying end-to-end ML and AI-powered solutions integrating large language model APIs with Python backends. Developing predictive and classification models with real-world datasets, applying advanced feature engineering and hyperparameter optimisation techniques. Collaborating on AI-driven projects with focus on model accuracy, inference speed, and business applicability. Performing structured EDA and statistical analysis on multi-domain datasets to extract actionable insights. Creating interactive dashboards and data visualisations using Python libraries (Matplotlib, Seaborn, Streamlit) for stakeholder reporting. Documenting analytical processes and model outcomes in well-structured Jupyter Notebooks for reproducibility.

Data Science Intern

Enlighten Infosystems

Dec 2024 - Nov 2025

Engineered end-to-end ML pipelines covering raw data ingestion, preprocessing, feature engineering, model training, hyperparameter tuning, and evaluation using Python and Scikit-learn. Built a T20 cricket match outcome prediction model using SVC and KNN algorithms; applied GridSearch hyperparameter tuning and k-fold cross-validation, achieving the best-generalising configuration on unseen data. Systematically compared multiple classification algorithms, selecting the optimal model based on accuracy, ROC-AUC, and confusion matrix analysis. Performed in-depth EDA on datasets of 1,000+ records, identifying key performance patterns, outliers, and highest-impact features for downstream modelling. Applied robust preprocessing — null value imputation, label encoding, standard scaling, and outlier treatment — delivering clean, model-ready data consistently across projects. Translated analytical findings into structured reports with visualisations, presented to technical mentors. Maintained a version-controlled codebase using Git & GitHub; documented Jupyter Notebooks for reproducibility and team knowledge sharing. Worked collaboratively in a professional environment, meeting deadlines, incorporating mentor feedback, and iterating on model performance.