Mohammed Abrar Mohiuddin
Email: email@example.com Mobile: 361-***-****
LinkedIn: https://www.linkedin.com/in/abrarmohiuddin/ Chicago, Illinois 60642 EDUCATION:
Master’s in Computer Science Engineering. May 2020 Texas A & M University.
Graduate Coursework: Data Mining, Database Systems, Cloud Computing, Analysis of Algorithms, Mobile App Programming, Compiler Design, Operating Systems, Software Engineering. Bachelor’s in Information Technology May 2016
CVR College of Engineering and Technology.
Technologies: C, Python (Pandas, NumPy, Matplotlib, Scikit), Data visualization, SQL, Android App Programming, and Machine Learning.
Applications: Android Studio, Anaconda-Jupyter notebook, Tableau Desktop and MS SQL Server, Amazon SageMaker.
Data Visualization: Matplotlib, Seaborn, Advanced-Excel, Tableau Desktop. EMPLOYMENT:
Accenture Hyderabad, India
Data Scientist Jan 2017 - May 2018
Collaborated with the team of engineers to deliver actionable insights from huge volume of data, coming from quality control domain.
Worked on all phases of data mining, data cleaning, data collection, developing models, validation, visualization and analysis using different machine learning modelling algorithms utilizing Python libraries
(TensorFlow, Scikit, and Keras).
Applied dimensionality reduction techniques like Principal Component Analysis (PCA) to extract relevant optimal features from high dimensional data.
Carried out Sentiment Analysis on the feedback from the customer for the predictive analysis.
Performed Feature Engineering for the development of statistical models and Deep Neural Nets to improve prediction model's performance and flexibility.
Built predictive models using algorithms like Support Vector Machine, Decision tree, Naive Bayes Classifier, Random Forest, etc. using Python’s Scikit Learn Library.
Investigated large datasets to handle missing values, cleaned messy datasets and applied feature scaling to standardize range of independent variables using Tableau.
Evaluated various tracking matrices in Machine Learning models and improved overall accuracy. Data Analyst Jan 2016 – Dec 2016
Gathered user requirements, analyzed, and designed data solutions based on the requirements.
Performed data queries for backend using complex SQL queries to validate the consistency of the data.
Developed API's using Python and SQL Alchemy data models as well as ensured code quality by writing unit tests using Pytest.
Automated ETL data processing frameworks through the introduction of a holistic reporting blueprint that enhanced data and information analysis using Python, SQL, Github.
Performed data cleansing, data analysis, hypothesis testing, dimensionality reduction and data mining to help data scientists developing mathematical and statistical models.
Created various analytical reports from multiple data sources by blending data on multiple worksheet tabs and dashboard in Tableau Desktop.
Designed and maintained project document templates based on SDLC- Agile/Scrum methodology. PROJECTS:
Predictive Analytics of products and customer feedback survey : Description: Analysed, pre-processed, and visualized 2 million survey response datasets to study trends in the customer behavior. Leveraged statistical models to forecast customer satisfaction in Python to increase customer retention and maximize profits. Built model based on various machine learning techniques like Regression including Logistic and Naïve based with the libraries like Scikit-learn and SciPy. Analyzed sale performance of different items, performed sentiment analysis on customers feedback for the rating and created a model for the new item to predict its sale value. Visualized the data for clear understanding by creating dashboards in Tableau. Environment: Python (Numpy, Pandas, Matplotlib), Machine Learning (K-nearest neighbors, Regression), SQL, Data visualization.
IDE Tools: Anaconda Jupyter Notebook-Python, Machine Learning, MS Server-SQL, Tableau- Data visualization. Major’s Academic Project
Sale Estimation Analysis based on ML modeling techniques: Description: Estimating the sale value of a house by building a model based on trained data from other houses in the area observations and then used to make a prediction about the value of the house. Examining a large data set of past home sales data acquired from the various data sources and finding patterns and statistical relationships between a house’s characteristics (features) and its price (the target variable).Using these statistical relationships and patterns to predict and estimate the value and the price of any new houses data. Created various dashboards for data visualization in Tableau desktop for clear understanding.
Environment: Python (Numpy, Pandas, Matplotlib), Machine Learning (K-nearest neighbors, Regression), SQL, Data visualization.
IDE Tools: Anaconda Jupyter Notebook-Python, Amazon SageMaker-Machine Learning, MS Server-SQL, Tableau- Data visualization.