NAGA SAI SUPRAJA PASUMARTHI

Jr. Data Analyst

Wilmington, Delaware, 19810 / 216-***-**** / www.linkedin.com/in/suprajapasumarthi / adwmz1@r.postjobfree.com

A highly motivated and enthusiastic student with a Master’s Degree in Information Assurance, Post Graduate Certificate in Data Science and a Bachelor's degree in Information Technology. I have 3+ years of experience as Jr. Data Analyst and coding with analytical programming using Python, Tableau and R Programming. Outstanding team member with exceptional interpersonal and problem-solving abilities, sound organizational, logical, problem-solving & communication skills, and working well both individually and in collaboration with an outgoing personality. Looking for a position to fit myself in an integral part of a team and dynamical professional environment. A punctilious, fast learner offering the ability to access an organization's need and create a complementary, robust web presence.

CORE QUALIFICATIONS:

Extensive experience working in Python, R Programming and Tableau.

Good knowledge in Shell Scripts.

Handley Experience with Data Modeling in Oracel database.

Have good knowledge with HTML.

Wrote Python and R routines to log into the websites and fetch data for selected options.

AREAS OF EXPERTISE:

Programming languages: Python, R Programming, Tableau, Power BI, SQL, MatLab.

Technologies: HTML.

Databases: Oracle.

Software: Microsoft PowerPoint, Microsoft Word, Microsoft Excel, Microsoft Outlook.

Operating Systems: UNIX, Liux, Windows, Mac OS.

Soft Skills: Trained regarding how to work in Corporate World with standards, rules, discipline, Event Organization, Project Management and subject knowledge.

Languages: English, Hindi, Telugu.

Typing Speed: 42 Words Per Minute.

PROFESSIONAL EXPERIENCE:

Arthasastra Intelligence Databases Private Limited, April 2020 to July 2021

PYTHON DEVELOPER

In Cyber Analysis Project, I worked on Churn of Bank Customers. The dataset consists of 14 rows with 10001 columns.

Credit Score of every customer is recorded for further use of Churn with the credit cards. Geography/Nationality of the customer is also an extra data of the customer that is recorded.

Age, Tenure of the Credit Maintenance and Balance of the credit available of the customers are used in estimating those customers credit scores in future.

Number of products bought by using the credit card for increasing the credit score is recorded for further usage.

Credit card or not, is specified for every customer for identifying whether they have a credit card currently or not. The Target variable for this dataset is Exited.

This target variable for the dataset is saved in binary format i.e., 0 and 1. This dataset is a case of Logistic Regression, which is the most utilized regression model in readmission prediction, given that the output is modelled as readmitted (1) or not readmitted (0).

This regression model is used to estimate the relationship between a dependent variable and one or more independent variables, but it us used to make a prediction about a categorical variable versus a continuous one.

The Churn for Bank Customers project, which aims to determine which supervised statistical learning processes, such as Random Forest, Logistic Regression, or K-Nearest Neighbour, is the most effective at predicting bank customer churn.

A predictive model was constructed under the project using Multi-Layer Perceptron of Artificial Neural Network architecture, Python programming language, and two overfitting techniques to predict customer churn in financial institutions.

The Crop Recommendation System is a smart android application that aids farmers in significantly increasing productivity.

Based on current weather and soil conditions, the application uses data analytics techniques to predict the most profitable harvest.

Using data from the repository and the weather department, and the Machine Learning algorithm Multi Linear Regression, a prediction of the most appropriate crops is made based on current environmental conditions.

This provides a farmer with a diverse crop selection.

it incorporates data from various sources, performs data analytics, and conducts prediction analysis to improve crop yield performance and raise farmer profit margins.

Environment: R Programming, Python, Tableau, JSON, GitHub

PROFESSIONAL EXPERIENCE:

Arthasastra Intelligence Databases Private Limited, September 2019 to April 2020

INTERN

The Movie Recommendation System that filters data using various algorithms and recommends the users' most interesting things.

It begins by capturing a customer's history and then suggests items that the users are likely to purchase based on that information.

If a user visits an e-commerce site for the first time, the site would have no previous history with that user.

The system's basic premise is that films that are more successful and critically praised are more likely to be liked by the general public.

The second type of filtering is content-based filtering, in which we try to profile a user's preferences based on the data we collect and then suggest products based on that profile.

The other is collective filtering, in which we attempt to group similar users and use group knowledge to make suggestions to the user.

In Helmet Detection Project, Motorcycle accidents have been rapidly growing through the years in many countries. In India more than 37 million people use two wheelers.

Therefore, it is necessary to develop a system for automatic detection of helmet wearing for road safety. Therefore, a custom object detection model is created using a Machine learning based algorithm which can detect Motorcycle riders.

On the detection of a Helmetless rider, the License Plate is extracted and the License Plate number is recognized using an Optical Character Recognizer.

This Application can be implemented in real-time using a Webcam or a CCTV as input.

Environment: R Programming, Python, Tableau, JSON, GitHub.

PROFESSIONAL EXPERIENCE:

INSOFE, May 2019 to August 2019

INTERN

In Hotel Recommendation System, AI Databases will build an application which takes input data from the user and predicts which hotels are suitable for the customer on the basis of their location, budget and other requirements.

The data is scrapped from different sources and the application is build.

In this project, scrap, pre-process, building the modeling of the algorithms were performed and also performed the clustering on the necessary hotel recommendation data to AI Databases, which will further be used for recommendation building purpose.

Visualizations and recommendation systems were built related to the data provided by AI Databases.

The data sets used for this purpose specifically consists of New and Old Hotels in Hyderabad, with their specific ID, customers with their specific ID and their ratings to both new and old hotels with which we develop a recommendation system.

Environment: R Programming, Python, Tableau, GitHub.

PROFESSIONAL EXPERIENCE:

RIIS Private Limited, May 2017 to October 2018

JR. DATA ANALYST

In Synthetic Financial Datasets for Fraud Detection, there is a lack of publicly available datasets on financial services and specially in the emerging mobile money transactions domain.

Financial datasets are important to many researchers and in particular to us performing research in the domain of fraud detection.

Part of the problem is the intrinsically private nature of financial transactions, that leads to no publicly available datasets.

We present a synthetic dataset generated using the simulator called PaySim as an approach to such a problem.

PaySim uses aggregated data from the private dataset to generate a synthetic dataset that resembles the normal operation of transactions and injects malicious behavior to later evaluate the performance of fraud detection methods.

PaySim simulates mobile money transactions based on a sample of real transactions extracted from one month of financial logs from a mobile money service implemented in an African country.

The original logs were provided by a multinational company, who is the provider of the mobile financial service which is currently running in more than 14 countries all around the world.

This synthetic dataset is scaled down 1/4 of the original dataset and it is created just for Kaggle.

In Indian Driving Dataset, driving front facing camera images from Hyderabad and Bangalore are taken.

While several datasets for autonomous navigation have become available in recent years, they have tended to focus on structured driving environments.

This usually corresponds to well-delineated infrastructure such as lanes, a small number of well-defined categories for traffic participants, low variation in object or background appearance and strong adherence to traffic rules.

We propose a novel dataset for road scene understanding in unstructured environments where the above assumptions are largely not satisfied.

It consists of 10,000 images, finely annotated with 34 classes collected from 182 drive sequences on Indian roads.

The label set is expanded in comparison to popular benchmarks such as Cityscapes, to account for new classes.

The dataset consists of images obtained from a front facing camera attached to a car. The car was driven around Hyderabad, Bangalore cities and their outskirts.

The images are mostly of 1080p resolution, but there are also some images with 720p and other resolutions.

Environment: Java, MatLab, R Programming, Python, Tableau, JSON, GitHub.

Contact this candidate