SAI GAURAV DAULA

**** ************* ****, *******, ** 22031 202-***-**** adlylm@r.postjobfree.com LinkedIn profile-Sai Gaurav Daula SUMMARY

Curious, vivacious, and innovative professional with the capacity to quickly incorporate complex ideas in a cross-practical condition. Seeking after a challenging profession and be a piece of reformist association that gives an extension to upgrade my insight and using my abilities towards the development of the association. Have experience in working with large database and have performed duties of managing and implement my technical skillset and knowledge at work.

SKILLS

Languages: Python, R, EXCEL, HTML, C, JAVA, MATLAB, Linux. Databases: SQL, NoSQL, Hive.

Machine Learning packages: NLP techniques, NLTK, TensorFlow, Pytorch, Keras, Sklearn, Pandas, NumPy, Matplotlib, Time series Analysis, Clustering techniques, Fuzzy Matcher, Latent Dirichlet allocation (LDA) techniques, Regex, Vectorization. Tools: Alteryx, Tableau, Weka, GGPlot.

Statistical Techniques: Linear and Integer programming. PROFESSIONAL EXPERIENCE

Project Intern Jan 2021 – May 2021

Federal Aviation Administration (FAA) Fairfax, VA

• Worked as a developer on the FAA data, to bring out valuable insights and semi-automize a system to accident/incident detection.

• Used visualization tools and programing languages such as Python, R, SQL, Tableau, Excel so as to work and finish the project.

• Pre-processing raw data and processed to bring meaningful insights, data for further analysis.

• Integrating data from different datasets, understanding common features across all datasets, and then applying techniques for grouping the data.

• Understanding and putting it into practice combining strategies in order to get all of the data into a single repository.

• Using natural language processing (NLP) techniques to extract information from text fields in a combined or blended dataset. Part-time Student worker in Technical team at Admissions office Jan 2020 - Present George Mason University Fairfax, VA

• Managing and working with student databases from production to release of application.

• Worked with huge database involving jobs like inserting data, retrieving data, sorting, managing applications of students and the database itself.

• Worked on few projects on the administrative interface the Internet Native Banner, which is used by authorized professionals of the university. Application developer Intern June 2019 – July 2019 Electronic Corporation of India Ltd. Hyderabad

• Built an application to ease the way a client purchases their medication by uploading a certified prescription in the application upon authorization from experts they can have them delivered to door by the nearest pharmacy. Clients can also track their medication usage, the side effects and the expiry of their medication.

• We built a user-friendly interface that allows individuals from all age groups to understand and use the application easily.

• To achieve the end product and complete a project with such high complexity we used technologies like SQL,C, Java.

• We used HTTP and FTP protocols for transfer of information. EDUCATION

George Mason University, Fairfax, VA Expected Grad: May 2021 M.Sc. Data Analytics Engineering; GPA - 3.78

Relevant Coursework: Intro to Natural Language Processing; Big Data needs Analytics; Data mining in Health care; Info : Represent, Process & Visualize; Principles of Data Mining/Management; Applied Predictive Analytics; Applied Statistics & Visualization for Analytics, Analytics for Big data to information; Analytics/Decision Analysis.

PROJECTS

Data Analysis on Bank Marketing Data GitUrl Data Analytics, Clustering R, PAM, Lasso, Random forest Classifier,GGPLOT

• Predicted client term deposit subscriptions and isolated information into various clusters, inferred client designs and examined the conduct of clients through performing PAM clustering and representations in GGPLOT, helping increment subscriptions and help in crusade the executives.

• Handled the disproportioned Dataset by oversampling, at that point utilized the Lasso Model for feature selection, Normalization as Feature Engineering step and Random forest Classifier is utilized for prediction with an accuracy of 94% and PAM is utilized as Clustering Technique in R.

Predicting Violent Crimes per 100K Population according to 1990 US census GitUrl Data Analytics R, CART, Random forest Classifier, PCA, Linear Regression, GGPLOT

• Performed Pre-processing on the dataset and dealt with a lot of imbalanced information, predicted which factors do contribute in terms of crimes in a society, analyzed if any factor had significant contribution towards the crime rate.

• Performed (CART) Regression trees algorithm on the dataset to partition the dataset and fit a model, Performed Random forest classification and generated a Variable importance plot to identify the most important variable that can be used for predicting the final attribute.

• Handled the overlapping data by performing PCA on the dataset and successfully reduced overlapping on dataset from 113 attributes to 43 attributes with 95% variance.

• Performed Linear Regression to achieve an R-square of 96.92% and represented the data in GGPLOT.

• Performed Lasso and Ridge Regression with an output R-square of 96.94% and 96.92% respectively on the dataset and generated plots using GGPLOT.

SMS Spam Detection Data Analytics Natural Language Processing Python, Pickle, HTML, Flask, TensorFlow, TF-IDF Vectorizer, Counter Vectorizer, Naïve Bayes, Random Forest Classifier, SVM Classifier, Logistic Regression

• Predicted whether a message is Spam or Ham by user input. Performed various functions to check the accuracy of the data.

• Performed Exploratory Data Analysis on the data and used MatPlot library. Also performed data pre-processing on the data. Checked for stop words and the frequency of the Ham and Spam messages.

• Used Tf-idf and counter vectorizer to convert the data into vectors. Checked for accuracy of the data on various models like Naïve Bayes, Random Forest, Support Vector Machine, Logistic Regression.

• Created a Web application for a local server using Pickle. Heart Disease prediction using ML Data Analytics Python, MatPlot Library, Seaborn, Cross-Val scores, Logistic regression, K-Neighbors Classifier, Support Vector Classifier, Decision Tree Classifier, Gaussian Naïve Bayes

• Performed Pre-processing and predicted the accuracy of the data so as to confirm the heart disease of an individual.

• Performed correlation function to check the relation between each attribute, also used the MatPlot Library to project this data as graph.

• Performed Exploratory Data Analysis on the data.

• Predicted the accuracies using various models like Logistic regression, K-Neighbors Classifier, Support Vector Classifier, Decision Tree Classifier, Gaussian Naïve Bayes

• Used Cross Val Scores to check the variation in accuracies of the models. LEADERSHIP

Chairperson IEEE-SNIST May 2018 – May 2019

Sreenidhi Institute of Science and Technology Hyderabad, India

• Managed and coordinated the Technical Fest board team to organize related activities for more than 10,000+ students.

• Negotiated with diverse audiences and handled budgeting & finances for every initiative during the Fest. Public Relations Head ISTE-SNIST May 2018 – May 2019 Sreenidhi Institute of Science and technology Hyderabad, India

• Was responsible for making all the PR strategies and plans that promote the image and reputation of the cultural fest and the organization. Student Council head SNIST May 2018 – May 2019

Sreenidhi Institute of Science and technology Hyderabad, India

• Was responsible to monitor all the student organizations of the university to maintain a smooth functioning of all inter organization events. Secretary General WIE-CONFERENCIA 2.0 IEEE-SNIST May 2018 – May 2019 Sreenidhi Institute of Science and technology Hyderabad, India

• Wie conferencia is a 3- day national conference, the first of its kind event in IEEE circuit, associated with the IEEE affinity group Women in Engineering (WIE) organized by IEEE-SNIST.

• I fulfilled my responsibilities of managing the events, Post events work, and delegates along my team to make the event one of the sensational events of its time.

Vice-Chairperson IEEE-SNIST

Sreenidhi Institute of Science and technology Hyderabad, India

• Rendered services as the vice-chairperson with support of my Chairperson and managed the team and the events.

• Handled budgeting and finance of the organization.

Contact this candidate