__STYLES__

Omid Golchin Avatar

Omid Golchin

Aspiring Machine Learning Scientist Specialized in Revenue Analytics

About Omid

Maven credentials

Work experience

Education

Additional links

Sales Forecasting with PySpark: Predicting Retail Trends for Effective Inventory ManagementI developed a sales forecasting model using PySpark and Random Forest Regression to predict retail sales based on historical data. The model achieved a Mean Absolute Error (MAE) of 9.46 and predicted 89,120 units sold in week 39 of 2011.

Sales Forecasting with PySpark: Predicting Retail Trends for Effective Inventory ManagementI developed a sales forecasting model using PySpark and Random Forest Regression to predict retail sales based on historical data. The model achieved a Mean Absolute Error (MAE) of 9.46 and predicted 89,120 units sold in week 39 of 2011.

Automating Credit Card Approvals with Machine Learning: A Logistic Regression ApproachThis project automates credit card approval using the UCI dataset, achieving 79.39% accuracy with a tuned logistic regression model (max_iter: 100, tol: 0.01) through preprocessing, encoding, scaling, and hyperparameter optimization.

Automating Credit Card Approvals with Machine Learning: A Logistic Regression ApproachThis project automates credit card approval using the UCI dataset, achieving 79.39% accuracy with a tuned logistic regression model (max_iter: 100, tol: 0.01) through preprocessing, encoding, scaling, and hyperparameter optimization.

Optimizing Airline Fuel Spend with SARIMAX: A Time Series Forecasting ApproachDeveloped a SARIMAX-based model to forecast airline fuel expenditure for 2102, leveraging historical data. This project achieved high accuracy and identified trends, helping optimize operational budgeting with a predicted annual fuel spend of $1,7 M.

Optimizing Airline Fuel Spend with SARIMAX: A Time Series Forecasting ApproachDeveloped a SARIMAX-based model to forecast airline fuel expenditure for 2102, leveraging historical data. This project achieved high accuracy and identified trends, helping optimize operational budgeting with a predicted annual fuel spend of $1,7 M.

Sentiment-Based Clustering of Google Play Reviews Using K-Means and NLPThis project applies NLP to analyze negative Google Play reviews. By using K-means clustering and TF-IDF vectorization, I categorized the reviews into five clusters, revealing key insights into user frustrations such such as app crashes and poor UI/UX .

Sentiment-Based Clustering of Google Play Reviews Using K-Means and NLPThis project applies NLP to analyze negative Google Play reviews. By using K-means clustering and TF-IDF vectorization, I categorized the reviews into five clusters, revealing key insights into user frustrations such such as app crashes and poor UI/UX .

Building a Data Pipeline for Walmart's E-Commerce Analysis During HolidaysThe project involved merging, cleaning, and analyzing grocery sales data from a PostgreSQL database with complementary data stored in a Parquet file. Automated functions were created for data transformation, aggregation, and loading.

Building a Data Pipeline for Walmart's E-Commerce Analysis During HolidaysThe project involved merging, cleaning, and analyzing grocery sales data from a PostgreSQL database with complementary data stored in a Parquet file. Automated functions were created for data transformation, aggregation, and loading.

Comparative Analysis of Goal Scoring Trends in FIFA Men's and Women's World CupsUnveiling goal-scoring dynamics in international soccer: A statistical analysis reveals women's FIFA World Cup matches since 2002 tend to have more goals than men's. Using Python, pandas, and hypothesis testing, this study challenges perceptions and offer

Comparative Analysis of Goal Scoring Trends in FIFA Men's and Women's World CupsUnveiling goal-scoring dynamics in international soccer: A statistical analysis reveals women's FIFA World Cup matches since 2002 tend to have more goals than men's. Using Python, pandas, and hypothesis testing, this study challenges perceptions and offer

Decoding SaaS Subscription Renewal PatternsA data-driven analysis of subscription renewals for a SaaS company reveals that E-commerce leading renewal rates at 72.3%. The average inflation rate during renewals was 2.8%, hinting at economic factors influencing client retention.

Decoding SaaS Subscription Renewal PatternsA data-driven analysis of subscription renewals for a SaaS company reveals that E-commerce leading renewal rates at 72.3%. The average inflation rate during renewals was 2.8%, hinting at economic factors influencing client retention.

Predicting Insurance Premiums with Machine Learning This predictive analytics project leverages machine learning to forecast health insurance premiums by analyzing factors such as age, BMI, and smoking status. I've created a regression model that explains 75% of the variance in insurance charges.

Predicting Insurance Premiums with Machine Learning This predictive analytics project leverages machine learning to forecast health insurance premiums by analyzing factors such as age, BMI, and smoking status. I've created a regression model that explains 75% of the variance in insurance charges.

Manufacturing Process Control OptimizationImplemented statistical process control (SPC) in a manufacturing environment using SQL to analyze production data, set control limits, and flag out-of-range products, enhancing quality control and process efficiency.

Manufacturing Process Control OptimizationImplemented statistical process control (SPC) in a manufacturing environment using SQL to analyze production data, set control limits, and flag out-of-range products, enhancing quality control and process efficiency.

Video Streaming Platform Churn Predictor and Subscriber SegmentationDeveloped a high-performing churn prediction system achieving 92.5% accuracy using Logistic Regression, alongside identifying three distinct subscriber segments based on engagement patterns, enabling to implement data-driven retargeting initiatives.

Video Streaming Platform Churn Predictor and Subscriber SegmentationDeveloped a high-performing churn prediction system achieving 92.5% accuracy using Logistic Regression, alongside identifying three distinct subscriber segments based on engagement patterns, enabling to implement data-driven retargeting initiatives.

About Omid

Maven credentials

Work experience

Education

Additional links

Sales Forecasting with PySpark: Predicting Retail Trends for Effective Inventory Management

Automating Credit Card Approvals with Machine Learning: A Logistic Regression Approach

Optimizing Airline Fuel Spend with SARIMAX: A Time Series Forecasting Approach

Sentiment-Based Clustering of Google Play Reviews Using K-Means and NLP

Building a Data Pipeline for Walmart's E-Commerce Analysis During Holidays

Comparative Analysis of Goal Scoring Trends in FIFA Men's and Women's World Cups

Decoding SaaS Subscription Renewal Patterns

Predicting Insurance Premiums with Machine Learning

Manufacturing Process Control Optimization

Video Streaming Platform Churn Predictor and Subscriber Segmentation