Address **** ****** ********
Date of birth 1991-07-09
Skilled data analyst with more than 4 years of industry experience in collecting, organizing, interpreting,disseminating and reporting various types of statistical figures.Energetic presenter and confident communicator with experience in utilizing analytical & methodical skills to interpret and commute data with relevant expertise to help the company achieve business goals while sticking to vision, mission and value. A highly motivated and passionate individual, adept in reporting outcomes to provide efficient advice or projections. Actively seeking to leverage my technical and professional skills to learn and grow in your company. 2013-05 -
• Extracted, compiled, cleansed and tracked data, and analyzed data to generate reports.
• Converted data into actionable insights by predicting and modelling future outcomes.
• Developed optimized data collection and qualifying procedures.
• Leveraged analytical tools to develop efficient system operations.
• Performed daily data queries and prepared reports on daily, weekly, monthly, and quarterly basis.
• Extensively used Oracle and SQL for accessing database systems
• Performed in-depth analyses for business performance and corporate sustainability using SWOT and Microsoft Office Suite. Extensively used UML Use Case diagrams to communicate and Advance MS Excel to measure outcomes:
- 9.1% growth in revenue (2016)
- 303% net earnings (2017)
- 32% return on equity (2017)
- 30% upward in efficiency gains
- $371K capital-expense reduction
- $1.1M labor-cost savings
- 97% account-retention rates
• Presented data and reports to executives widely using MS Visio to present stakeholder ideas and improve operations using statistical techniques and successfully interpreted data.
• Monitored and controlled costs and tracked expenses, increasing sales and profits in 30%.
• Performed Deming Cycle on collaboration with stakeholder groups for business improvements.
• Performed risk analysis with complexity assessment using R and decision support tools to decrease error and mitigate possible risks.
Data Management skills: Database design and management, Data Quality assessment, Data Analysis, Data Manipulation,Forecasting,Pattern and trend identification, Data Insights and visualization. Programming Languages: Core Java, SQL, VBA, Python, R, Scala. Operating systems : Windows XP, Windows 7&10, Ubuntu. ETL tools : SSIS, SSAS, SSRS.
Big data technologies : Hadoop, Spark, Hive, PIG, Flume, Sqoop, Kafka, storm, Impala, NLP. Development Tools : Eclipse, PyCharm, R studio, Anaconda. Data visualization Tools: Tableau and PowerBI.
Web Designing : HTML, CSS, Java Script.
Database tools : Sql developer 3.0
Code repository tools: ClearCase 8.0.1, GitHub
Cloud services : AWS and Microsoft Azure
Machine learning and Deep learning algorithms: Linear, Logical Regression, Support vector machines, K means, Apriori algorithm, Principle component analysis (PCA), Singular value decomposition (SVD), CNN, RNN, LSTM, RBM, DBM, Autoencoders.
Lambton College of applied arts and technology
Big data science and Informatics
St.Martins Engineering college
A Social Network-Based Recommender System
• In this project we present a new paradigm of recommender systems which can utilize information in social networks, including user preferences, item's general acceptance, and influence from social friends.
• A probabilistic model is developed to make personalized recommendations from such information.
• Taken the scenario of Movie recommendation systems from social media data and predicting the Content based recommendations and User based recommendation systems based on that.
• Out of all approaches, Cosine similarity method worked well while designing the algorithm. Accuracy of the algorithm: Got the accuracy of 93.4 from RMSE method. (Chosen RMSE because of its accuracy)
Role in this project: I worked on the cleaning the data and implemented the user-item filtering. Languages and Techniques used: Python, R, Collaborative filtering Algorithms. Tools used: Jupyter Notebook and R studio.
Movies prediction using Matrix factorization method
• Used Principle Component Analysis (PCA) and Singular Value Decomposition (SVD) to recommend the movies to the users.
• Used this approach to recommend the movies to the users according to their tastes and preferences.
• Using PCA approach worked well to generate the principle component values of the users and the movies.
• Used Movie Lens dataset for the input data.
Role in this project: Implemented the SVD part of the project. Languages and Techniques used: Python.
Packages used: Pandas, NumPy.
Techniques used: Principle component analysis (PCA) and Singular valued decomposition (SVD) Accuracy : 91.7 through RMSE method. (Chosen RMSE because of its accuracy) Implementing Association rules on the Instacart dataset.
• Used market basket analysis on the Instacart dataset and implement the Apriori algorithm on that to calculate support, confidence and lift and to generate the recommendations from the user’s transactions.
• Generated recommendations of the most precise associations of the products. Tools used: Azure Machine learning studio to implement this algorithm. https://www.youtube.com/watch?v=DaKL4xj9TVQ
2019-05 Certified on Deep learning with TensorFlow from Cognitiveclass.Ai Taught Python classes to students through superprof.ca Attended various Big data conferences.