Professional Summary (Total Experience 4 Years 5 Months: Data Science)
    • Experienced Data Science Professional with 4 years 5 Months of experience in Data Science, Python, Machine Learning and Visualizations 
    • Having Strong Knowledge in implementing Supervised and Unsupervised Machine Learning Algorithms(Classification and Regression, Natural Language Processing ) by using Python Scikit Learn
    • Passion for data, coding, modelling, research design and cutting-edges algorithms. Track record of thought leadership and outstanding expertise in the area of data science.
    • Good understanding on Django ORM and SQLAlchemy.
    • Experienced in interfacing with third party API’s using REST and SOAP.
    • Experienced in developing web-based applications using Python, PHP, XML, JSON and MVC3.
    • Well versed in design and development of presentation layer for web applications using technologies like HTML, CSS, JavaScript, JQuery, AJAX and Bootstrap.
    • Responsible for ideate, frame, drive and manage use-cases applying to different market segments from a data science perspective, and help marketing and product stakeholders to improve customer acquisition, retention, experience and value. 
    • Responsible for build the data sciences pipelines to optimize the Who, When, Where and How of all our conversations with customers. Will skilfully balance short term benefits and long-term foundations when managing his time.
    • Thrived in complex business environments defined by uncertain, incomplete or limited information. Is comfortable dealing with ambiguities and evolving targets, and finding (or building) common ground to drive his agenda.
    • Customer- and business obsession, with a bias for action and a drive to create measurable value.
    • Engaged with stakeholders (including senior stakeholders like board of directors and VPs), enthuse them for data science benefits, and deliver in a professional, timely way. 
Skill Set
Supervised Machine Learning Algorithms
Linear Regression, Logistic Regression, Decision Trees, Random Forest, Naive Bayes, KNN
Unsupervised Machine Learning Algorithms
K-means , Agglomerative, PCA
Programming Languages
Python, Java
Visualization Tools 
Tableau
Databases
Db2, Teradata, SQL Server

Experience
    • Lumen Data Solutions India Pvt Ltd, Consultant, Bangalore, April’ 2019 –June 2019.
    • Shresta Info Global Services, Consultant, Hyderabad, Jan’ 2015 – March’ 2019.

Certification
    • IBM SPSS Modeler Professional Basic V3
Educational Qualification
    • B.Tech (2015) in the stream of Information Technology from Holy Mary Institute of Technology JNTUH University with 61%.
    • Intermediate (2011) in M.P.C from Sri Chaitanya Junior Kalasala Board of Intermediate Education, A.P with 56.7%. 
    • S.S.C (2009) from Mother Theresa High School Board of Secondary Education, A.P with 68%. 

PROJECTS:
Project: Identified the drivers of credit card sales for fortune 500 bank
Techniques: Linear Regression, Hypothesis Testing

Responsibilities:
    • Created the base dataset from multiple resource (i.e. Db2 and Sql Server).
    • Implemented EDA, Outlier treatment, Null value treatments and created the final analytical datasets.
    • Implemented K fold validation to check the accuracy of the models across different methods 
    • Computed R2, Adj R2, RMSE, MAE, MSE and shared the results with relevant stakeholders 
    • Compared the accuracy of Baseline models with Bench marking models.
Project: Helped in reducing the losses to fortune 500 Bank by identifying the   fraudulent credit card transactions 
Techniques: Logistic Regression, Random Forest
Responsibilities:
    • Responsible for designing test and train data sets and constructed the models using logistic and   Random forest techniques. 
    • Analysed the classification report, accuracy score and ROC curve to gauge the performance of the models. 
    • Identified the TPR and FPR for the models and communicated the KPIs to the stakeholders.
    • Increase the model accuracy by performing multicollinearity, variance inflation factor analysis.
Project: During the launch of the new Platinum card for high value customers, predicted the Renewal rate and helped in reducing the operation cost 
Techniques: Decision Tree and Random Forest

Responsibilities:
    • Visualized the patterns of credit card renewal through decision tree. Identified the prioritized variables by using information gain, ginning index, entropy and CHAID analysis. 
    • Constructed the tree with 10 levels and visualized the patterns in platinum credit card renewal programs.
    • Responsible for identifying the accuracy score, optimizing the type 1 and type 11 errors for the test data set and shared the key KPIs related to the business with relevant stake holders.
    • Used Python scripts to update the content in database and manipulate files.
    • Monitoring and finding the issues in the platform.
    • Ensuring that the applications being developed can be used by non-technical person.

Project: Measuring the impact of seasonal and promotional campaigns for Fortune 100 Retail company     
Techniques : K Mean clustering, Agglomerative Clustering

Responsibilities:
    • Created the customers segments based RFM Metrics and helped marketing team in defining the campaigns.
    • Created market segments and helped marketing team to start the new initiatives in each of the segments. 
    • Used K Mean and Agglomerative techniques to create the clusters and presented cluster groups to relevant stake holders.    
Project: Sentiment Analysis of Promotional campaign and seasonal programs
Techniques: Text mining 
Responsibilities:
    • Design, develop, and test applications for text processing, such as name or entity matching, text categorization/routing, named-entity extraction, sentiment analysis.

    • Created sentiment analysis dashboards for world’s largest retailer. Measured the impact of social media status and helped them in course correcting the future projects.

Responsibilities:
    • Involved in building database model, APIs and views utilizing Python, in order to build an interactive web based solution.
    • Used data types like dictionaries, tuples and object -concepts based inheritance features for making complex algorithms of networks.
    • Designed and developed the UI of the website using HTML, XHTML, AJAX, CSS and JavaScript.
    • Expertise in client scripting languages like JavaScript, JQuery, JSON, DOJO, bootstrap, Angular.js.
    • Designed and managed API system deployment using fast http server and Amazon AWS architecture.
    • Worked on Python Open stack API’s.
    • Carried out various mathematical operations for calculation purpose using python libraries.
    • Managed large datasets using Panda data frames and MySQL.
    • Worked with JSON based REST Web services.
    • Performed testing using Django’s Test Module.
    • Creating unit test/regression test framework for working/new code.
    • Using Subversion version control tool to coordinate team-development.