We provide IT Staff Augmentation Services!

Associate Software Engineer, Data Analyst Resume

SUMMARY:

Ardent computer science student with strong leadership and teamwork qualities skilled in Data Analytics, with a strong foundation in mathematics, logic and coding. Seeking a full - time job opportunity at your company for career advancement in Data Analytics/Data Science

TECHNICAL SKILLS:

Languages: C, C++, JAVA, SQL, PL/SQL, R, JavaScript, Python, PHP, Hadoop, Spark, Octave, PostgreSQL, T-SQL

Analytical Tools: Tableau, WEKA, QlikSense, MS-ExcelGoogle Analytics, QlikView, MATLAB

ERP: Oracle Applications, Oracle reports, Oracle Forms

Software Methodologies: Agile/Scrum, Iterative

Operating Systems: Linux, UNIX, Windows

Web Technologies: HTML, CSS, JSP, Servlets

Database Systems: Oracle 11g, My SQL, MongoDB

EXPERIENCE:

Confidential

Associate Software Engineer, Data Analyst

Responsibilities:

  • Worked on Complex, Large datasets related to the sales of the client which contained around 1million records
  • Performed Exploratory Data Analysis (EDA), Data Cleaning, Data Pre-processing, Data Modelling
  • Evaluated the performance of different modelling techniques like Decision trees, SVM, Logistic Regression
  • Fine-tuned the Decision tree, SVM algorithms using hyperparameter to perform better
  • Reduced the complexity of dataset by using dimensionality reduction technique i,e, PCA
  • Responsible for creating pivot tables in Excel and forwarding them to the Client
  • Developed a program which is responsible for firing emails using SMTP protocol when a requirement is met
  • Analyzed the dataset by cleaning and performing Exploratory Data Analysis (EDA), handled the missing values using Mice Package and used SQLDF library to merge related dataset files. Decision Tree, Logistic Regression, Neural Networks and K-Means Algorithms were used in determining the overall rating of a nursing home considering several important attributes and evaluated the performance of these models
  • Analyzed the data set which consists of 492 frauds out of 284000 transactions.
  • Handled the unbalanced dataset using SMOTE algorithm on training data set and thereby trained on Logistic Regression and Support Vector Machines(SVM) and calculated the recall where SVM showed better recall value.
  • Implemented the architecture of three different independent entities Doctor’s Module, Nurses Module and Pharmacy Module and later merged these entities different databases into a Data Lake using the concepts of data warehousing and designed the snow flake schema to make the information retrieval and decision making easy
  • Predicted whether an employee leaves the company or not by performing EDA, handled missing values, Oversampled the dataset, Used SVM and RandomForest Classifiers to predict the outcome. Evaluated the performance of models.

Hire Now