Shahanas M J

Shahanas M J

Data Scientist
Qatar
Malayalam, English, Arabic

About Me

"A motivated Data Scientist eager to leverage my strong programming skills in Python, analytical aptitude, and knowledge of data visualizations to accurately analyze, interpret, and present insights from large datasets. …

Experience

Data Analyst

Trainon Company, Ernakulam, India
Mar 2024 - Present · 2 years 4 months

Developed a real estate price prediction model using Linear Regression and Random Forest algorithms to predict property prices based on features like location, property size, and amenities.
Performed data cleaning and feature engineering on large real estate datasets, addressing missing values, outliers, and creating new variables (e.g., price per square foot) to improve model accuracy.
Implemented cross-validation techniques to assess model performance and reduce overfitting, achieving a mean absolute error (MAE) on the validation set.
Visualized key insights, such as the impact of location and neighborhood on property prices, using Matplotlib and Seaborn, helping stakeholders make data-driven decisions.
Preprocessed large datasets using Numpy, Pandas and Scikit-learn for feature selection and normalization, improving model performance.

Data Scientist

trainon
Jan 2024 - Present · 2 years 6 months

Dear Sir,

Dear sir,

I am eager to apply for the Data Scientist position in Qatar, where I am currently residing on a family residence visa. I bring strong programming skills in Python, experience in creating insightful data visualizations, and a solid foundation in machine learning algorithms gained through rigorous coursework and hands-on projects.

I hereby declare that all the above furnished information is true to the best of my knowledge.
Place:
Date:
Yours sincerely,
(Shahanas M.J)

Data Analyst

Trainon Company, Ernakulam, India
Mar 2024 - Present · 2 years 4 months

Developed a real estate price prediction model using Linear Regression and Random Forest algorithms to predict property prices based on features like location, property size, and amenities.
Performed data cleaning and feature engineering on large real estate datasets, addressing missing values, outliers, and creating new variables (e.g., price per square foot) to improve model accuracy.
Implemented cross-validation techniques to assess model performance and reduce overfitting, achieving a mean absolute error (MAE) of [specific percentage/amount] on the validation set.
Visualized key insights, such as the impact of location and neighborhood on property prices, using Matplotlib and Seaborn, helping stakeholders make data-driven decisions.
Preprocessed large datasets using Numpy, Pandas and Scikit-learn for feature selection and normalization, improving model performance.

Skills

Python Data Validation Html C++ Visual Studio Code Jupyter Notebook MySQL Google Colab Pandas NumPy Matplotlib Seaborn Plotly Scikit-learn Selenium Problem-solving Communication Team Collaboration Customer Acquisition Presentation Dashboards Resolving Issues Organization Skills HTML Linear Regression Random Forest XGBoost
Report this Profile?