Amit Sunil

Highly motivated and detail-oriented Fresher Data Analyst with a strong foundation in data analysis, visualization, and reporting. Skilled in developing and implementing data collection systems, identifying business needs, and creating predictive models that improve forecasting accuracy. Proven ability to collaborate with cross-functional teams and deliver data-driven insights that drive revenue growth and operational efficiency.

Nationality: Indian

• English, Proficient
• Hindi, Fluent
• Malayalam, Native proficiency
• German, Currently learning

Travel Enthusiast: Passionately traveled to various places, capturing stunning landscapes and cultural moments through photography, and enhancing personal growth and understanding of diverse cultures. 

 Reader: Regularly read a wide range of books, from fiction to non-fiction, to broaden knowledge and improve analytical thinking and comprehension skills. 

Motorcycle Riding: Enjoyed riding motorcycles on long journeys, developing a sense of adventure, independence, and an appreciation for the open road.

Sales Forecasting System

• Objective: Developed a sales forecasting model to predict future sales trends for a retail company, helping them optimize inventory and improve supply chain management.
• Data Collection and Cleaning: Collected historical sales data from various sources, including POS systems and e-commerce platforms, and cleaned the data using Python libraries such as Pandas and NumPy to ensure accuracy and consistency.
• Feature Engineering: Performed feature engineering by extracting important variables such as seasonality, holidays, and promotional events to enhance the predictive power of the model.
• Model Development: Implemented multiple machine learning models, including ARIMA, XGBoost, and LSTM, and used cross-validation to select the best-performing model based on accuracy and mean absolute error (MAE).
• Model Evaluation: Evaluated the model's performance using metrics like RMSE and MAE, and conducted backtesting to ensure the model's robustness and reliability.
• Deployment and Monitoring: Deployed the final model using Flask and Docker, and set up a monitoring system to track the model's performance over time and update it as necessary.
• Outcome: Achieved a 15% improvement in forecasting accuracy, leading to better inventory management and a reduction in stockouts and overstock situations.

Customer Segmentation Analysis 

• Objective: Conducted a customer segmentation analysis for an e-commerce company to identify distinct customer groups and tailor marketing strategies accordingly.
• Data Preparation: Gathered customer transaction data, including purchase history, demographics, and website behavior, and cleaned the data to remove any inconsistencies or missing values.
• Exploratory Data Analysis: Performed exploratory data analysis (EDA) using Python and visualization libraries like Matplotlib and Seaborn to understand the distribution and patterns in the data.
• Clustering Techniques: Applied clustering techniques such as K-means and hierarchical clustering to segment customers into distinct groups based on their purchasing behavior and demographics.
• Segmentation Insights: Analyzed the characteristics of each customer segment and identified key insights, such as high-value customers, frequent buyers, and price-sensitive shoppers.
• Recommendation System: Developed a recommendation system to suggest personalized products to each customer segment, enhancing customer satisfaction and increasing sales.
• Outcome: Enabled the marketing team to create targeted campaigns for different customer segments, resulting in a 20% increase in customer engagement and a 10% boost in sales.

 Sentiment Analysis of Social Media Data

• Objective: Performed sentiment analysis on social media data to gauge public opinion on a new product launch and provide actionable insights to the marketing team.
• Data Extraction: Extracted data from social media platforms like Twitter and Facebook using APIs and web scraping techniques, focusing on mentions of the new product.
• Data Cleaning: Cleaned and preprocessed the text data by removing noise, handling missing values, and performing tokenization, lemmatization, and stop-word removal.
• Text Analysis: Used Natural Language Processing (NLP) techniques and libraries such as NLTK and spaCy to analyze the sentiment of the text data and categorize it as positive, negative, or neutral.
• Machine Learning Model: Trained machine learning models, including logistic regression and random forests, to classify the sentiment of social media posts.
• Visualization and Reporting: Created interactive dashboards using Tableau and Python to visualize sentiment trends over time and highlight key insights for the marketing team.
• Outcome: Provided the marketing team with real-time insights into customer sentiment, enabling them to adjust their strategies and improve the product's reception, ultimately leading to a 12% increase in positive sentiment.

Predictive Maintenance for Manufacturing

• Objective: Developed a predictive maintenance system for a manufacturing company to predict equipment failures and schedule maintenance, reducing downtime and operational costs.
• Data Collection: Collected sensor data from manufacturing equipment, including temperature, vibration, and usage data, and performed data cleaning to ensure data quality.
• Feature Engineering: Created new features by analyzing the sensor data and identifying patterns that indicate potential failures, such as thresholds and anomaly detection.
• Model Development: Implemented machine learning models, including random forests and gradient boosting, to predict equipment failures based on historical sensor data.
• Model Evaluation: Evaluated the model's performance using precision, recall, and F1-score, and conducted cross-validation to ensure the model's reliability and accuracy.
• Deployment: Deployed a predictive maintenance system using a cloud-based platform, integrating it with the company's existing infrastructure for real-time monitoring.
• Outcome: Successfully reduced unexpected equipment failures by 25% and maintenance costs by 15%, improving overall operational efficiency and productivity.