Rishabh Shrivastava

Eager to leverage my analytical skills, passion for data, and commitment to continuous learning in a transition to the IT field as a Data Scientist or Data Analyst. Possess a solid foundation in data analysis concepts and a strong willingness to learn and adapt to new technologies and methodologies.

Real Estate 

Objective: Conducted data science analysis to gain insights into real estate market dynamics and develop predictive models for property prices.

Data Collection: Gathered comprehensive real estate dataset containing property attributes, transactional information, and market trends.

Data Cleaning and Preprocessing:

• Cleaned and standardized data to ensure accuracy and consistency.
• Handled missing values and outliers to maintain data quality.

Exploratory Data Analysis (EDA):

• Uncovered patterns and relationships between property features and prices.
• Visualized price distributions, property types, and location-based trends.
• Identified potential predictors influencing property values.

Feature Engineering:

• Engineered new features like "location desirability" based on local amenities.
• Transformed variables for improved model performance.

Predictive Modeling:

• Employed regression algorithms (e.g., linear, Lasso, Ridge) to predict property prices.
• Utilized ensemble methods (e.g., Random Forest, Gradient Boosting) for robust predictions.
• Employed techniques such as cross-validation and hyperparameter tuning.

Model Evaluation:

• Evaluated model performance using metrics like Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).
• Ensured models generalize well to new data.

Insights and Recommendations:

• Discovered the significant impact of location and specific amenities on property prices.
• Identified factors that potential buyers can focus on to maximize property value.
• Provided actionable insights for real estate professionals to guide pricing and investment decisions.

Visualization and Reporting:

• Created interactive visualizations and dashboards to illustrate trends and model predictions (Tableau).
• Enhanced stakeholder understanding through clear and informative data representations.

Conclusion: The real estate data science analysis successfully harnessed data insights to provide a deeper understanding of property value drivers. The project's outcomes have the potential to revolutionize decision-making within the real estate industry, leading to more informed investments and strategic pricing strategies.

Data Science With Python

• Got 2 time Employee of the month Certificates In the month of June & August(2021) and 4 time in 2022 in the months of April, July, Sep & November.
• GOT 3 times V achiever Certificate (highest sales revenue in the region) in a row in Vedantu .
• GOT best BDA certificate In the UP region in BYJUS in the month of July 2020.

Healthcare. 

Objective: Conducted data science analysis to gain insights into healthcare trends, optimize patient care, and enhance operational efficiency.

Data Collection: Gathered a diverse dataset encompassing patient demographics, medical history, treatment records, and diagnostic tests.

Data Cleaning and Preprocessing: Thoroughly cleaned and preprocessed the data to address missing values, outliers, and inconsistencies.

Exploratory Data Analysis (EDA):

• Uncovered correlations between patient characteristics and medical outcomes.
• Visualized disease prevalence, age distribution, and gender-based health patterns.
• Identified potential predictors of readmission rates and treatment response.

Feature Engineering:

• Engineered new features like risk scores based on comorbidities.
• Transformed categorical variables into numerical representations for modeling.

Predictive Modeling:

• Utilized machine learning algorithms like Random Forest and Gradient Boosting.
• Built predictive models to forecast patient readmission likelihood and treatment success.
• Employed time series analysis for forecasting patient volumes and resource requirements.

Model Evaluation:

• Evaluated models using metrics such as accuracy, precision, recall, and F1-score.
• Conducted cross-validation to ensure generalization and minimize overfitting.

Insights and Recommendations:

• Discovered factors influencing readmissions, enabling targeted intervention strategies.
• Identified patient groups more likely to respond positively to specific treatments.
• Recommended resource allocation based on predicted patient volumes.

Visualizations and Reporting:

• Created interactive dashboards with visualizations to aid stakeholders' understanding.
• Generated heatmaps, line charts, and bar graphs to convey trends and patterns.

Conclusion: The healthcare data science analysis successfully leveraged data-driven insights to inform decision-making, resulting in improved patient care and operational efficiency. The project's outcomes have the potential to drive positive changes in healthcare practices and contribute to better health outcomes for patients.