Vikas Chitturi

Bengaluru, Karnataka, India
2K followers 500+ connections

Join to view profile

About

At Work, I'm a Data and ML Engineer, keenly interested in end-to-end flow of ingesting…

Services

Request proposal

Activity

2K followers

See all activities

Experience & Education

  • DAT Freight & Analytics

View Vikas’s full experience

See their title, tenure and more.

Join with email

Already on LinkedIn?

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

Licenses & Certifications

Join now to see all certifications

Volunteer Experience

  • BITS Pilani, Hyderabad Campus Graphic

    Logistics and Pitching Team Member of Placement division

    BITS Pilani, Hyderabad Campus

    - 4 months

    Education

    1. Logistics involves assistance to companies visiting our college looking for freshers having distinguished Skill Sets.
    2. Pitching entails Connecting with HR of a company and pitching your idea of hiring from your college by disclosing your Student's Talents and Skills.
    3. The Skills that are required here are People Management Skills, Communication Skills, Talking Skills, Coordination Abilities.

  • BITS Pilani, Hyderabad Campus Graphic

    Student Member - Student Mentorship Program

    BITS Pilani, Hyderabad Campus

    - 4 months

    Science and Technology

    1.Part of Student Mentor ship Program for a Semester in my First Year.
    2. Contributed and learnt some very important things like Knowledge Sharing, acquiring and following the guidelines from Seniors in Education, Choosing a right Career Path etc.

Courses

  • Advanced Integral Calculus

    MATH F111 - Secured 9/10

  • Advanced Mechanics Of Solids

    ME F211 - Secured 7/10

  • Algebra - Group Theory

    MATH F215 - Secured 7/10

  • C language

    CS F111 - Secured 7/10

  • Cosmology

    MATH F456 - Secured 9/10

  • Data Mining

    CS F415 - Secured 8/10

  • Discrete Mathematics

    MATH F213 - Secured 5/10

  • Fluid Mechanics

    ME F212 - Secured 6/10

  • Graphs and networks

    MATH F243 - Secured 6/10

  • Introduction to Functional Analysis

    MATH F341 - Secured 4/10

  • Linear Algebra

    MATH F112 - Secured 7/10

  • Machine Design and Drawing

    ME F241 - Secured 7/10

  • Machine Learning

    Secured 8/10

  • Mathematical Methods

    MATH F241 - Secured 8/10

  • Mathematics - III

    MATH F211 - Secured 9/10

  • Number Theory

    MATH F231 - Secured 6/10

  • Numerical Analysis

    MATH F313 - Secured 6/10

  • Operations research

    MATH F242 - Secured 7/10

  • Optimization

    MATH F212 - Secured 7/10

  • Probability distributions

    MATH F113 - Secured 8/10

  • Production Techniques

    ME F313 - Secured 7/10

  • Report writing

    -

  • Statistical Inference and Applications

    MATH F353 - Secured 7/10

  • Thermodynamics

    ME F214, BITS F111 - 8/10

  • Topology

    MATH F311 - Secured 5/10

Projects

  • Github Event Ingestion Pipeline

    -

    Ingestion script that consumes events generated on Github in the form of stars, comments and other impressions in batch mode and computes insightful metrics on top.

    https://github.com/absognety/git-integrate/blob/master/README.md

  • Assignment - Predictive Analytics - Machine Learning (As a part of Recruitment Criteria)

    -

    Environment: R

    1. Worked on Sample data set of American Voting Population with Target Variables of Republican and Democratic Candidates.
    2. Used Classification models - Decision trees, Random Forest and Binomial Logistic Regression to classify the population having the propensity to vote either of the Candidates.
    3. Constructed Confusion Matrices for all the Classifiers.
    4. Achieved an average accuracy of 71% on all three models.
    5. Concluded that Random Forest is the best…

    Environment: R

    1. Worked on Sample data set of American Voting Population with Target Variables of Republican and Democratic Candidates.
    2. Used Classification models - Decision trees, Random Forest and Binomial Logistic Regression to classify the population having the propensity to vote either of the Candidates.
    3. Constructed Confusion Matrices for all the Classifiers.
    4. Achieved an average accuracy of 71% on all three models.
    5. Concluded that Random Forest is the best Classifier among all other Classifiers for the data for its highest accuracy.

  • Optimization of Process Parameters in Manufacturing Processes

    -

    1. Mainly Studied Casting Process and various entities and parameters involved in it.
    2. Exclusively worked on Stir Casting process which is used in manufacturing Metal Matrix Composites like Aluminium metal Matrix Composites.
    3. Referred some journals and decided upon some crucial parameters affecting the final product in the process in terms of its strength, versatility, Stiffness and Stress endurance etc.
    4. Applied Multi - Attribute Decision making Techniques like Technique of…

    1. Mainly Studied Casting Process and various entities and parameters involved in it.
    2. Exclusively worked on Stir Casting process which is used in manufacturing Metal Matrix Composites like Aluminium metal Matrix Composites.
    3. Referred some journals and decided upon some crucial parameters affecting the final product in the process in terms of its strength, versatility, Stiffness and Stress endurance etc.
    4. Applied Multi - Attribute Decision making Techniques like Technique of order preference by similarity to Ideal Solution (TOPSIS) to determine the hierarchy of the impacting parameters.
    5. Used Taguchi methods in Design of Experiments for determining optimum values of parameters accepted.
    6. Using packages like "topsis" and "qualityTools" in R, these techniques have been coded leaving the choice for user to select finite number of quantities among the given.
    7. Signal to Noise ratio plots and orthogonal array selections have been incorporated in the code - Random experimental runs are generated depending on number of quantities chosen.
    8. Recommendations and Challenges have been addressed.

    See project

  • Java Implementation Of Association Rule Mining Algorithms (Market Basket Analysis)

    -

    1. Rule Generation in Association Rule Mining using Apriori Algorithm has been implemented in Java.
    2. The data was supervised learning task with Binary Outcome - Taken from UCI Machine Learning Repository.
    3. Frequent Item sets are stored using Tree structures, Especially by using hash trees.
    4. Code is taken from Github.
    5. Pre-processing of the data (Imputation of missing Values using k-NN or Naive Bayes Classifier) can be done using either R or Weka (Open Source Machine…

    1. Rule Generation in Association Rule Mining using Apriori Algorithm has been implemented in Java.
    2. The data was supervised learning task with Binary Outcome - Taken from UCI Machine Learning Repository.
    3. Frequent Item sets are stored using Tree structures, Especially by using hash trees.
    4. Code is taken from Github.
    5. Pre-processing of the data (Imputation of missing Values using k-NN or Naive Bayes Classifier) can be done using either R or Weka (Open Source Machine Learning Library in Java).
    6. Rule generation is achieved also by using FP-trees (Frequent Pattern Trees) - An alternative approach for Frequent Item Sets generation.
    7. Algorithm is experimented with several possible Support and Confidence Values. Observations are made on number of rules as support and confidence vary.

  • Machine Learning - Andrew NG - Stanford University - Coursera

    -

    1. Have been introduced to Several Machine Learning Supervised and Unsupervised algorithms such as Linear Regression, Logistic Regression, Neural Networks, Anomaly Detection, Clustering algorithms, Kernels and Distance functions etc.
    2. Recommendation Systems
    2, Advantages, benefits and ongoing research of Machine Learning.

    See project

  • Hidden Markov Models in DNA using R

    -

    1. A hidden Markov model (HMM) is a statistical Markov model in which the system being modeled is assumed to be a Markov process with unobserved (hidden) states.
    2. Hidden Markov Models are implemented in the DNA Setup using R using HMM Package.

  • Domination number of Butterfly Graphs

    -

    This Project is based on Mathematics and Programming. We dealt with the domination part of Graphs in specific for the class of graphs called Butterfly Graphs whose algorithms are used in Computer Networks and Discrete Mathematics.

    Responsibilities:-

    1. Referred journals on Domination numbers of Complete Grid Graphs, Restrained Double domination number of a Graph.
    2. Identified formula for generating domination number for higher order butterfly graph of order n.
    3…

    This Project is based on Mathematics and Programming. We dealt with the domination part of Graphs in specific for the class of graphs called Butterfly Graphs whose algorithms are used in Computer Networks and Discrete Mathematics.

    Responsibilities:-

    1. Referred journals on Domination numbers of Complete Grid Graphs, Restrained Double domination number of a Graph.
    2. Identified formula for generating domination number for higher order butterfly graph of order n.
    3. Constructed Butterfly Graph of order 1 and recursively generated Butterfly graphs of orders 2,3,4 and 5.
    4. Added levels and Connected Vertices (levels are represented as binary strings and connected if bits difference is 1 or 2 based on the problem.
    5. Finally identified the domination number.

    Under the Supervision Of Dr. Jonnalagadda Jagan Mohan

    http://universe.bits-pilani.ac.in/hyderabad/jonnalagadda/Profile

  • Modular Arithmetic

    -

    1. For a positive integer n, two integers a and b are said to be congruent modulo n, written: a ≡ b ( mod n ) , {\displaystyle a\equiv b{\pmod {n}},\,} if their difference a − b is an integer multiple of n (or n divides a − b). The number n is called the modulus of the congruence.
    2. Congruent Modulo Applications are tested on larger numbers using C Programming Language using different data types.

Honors & Awards

  • Topaz Award For Performance

    RADA, Optum Operations - United Health Group Company

    For getting 3rd position in MIndSpark - Analytics Fest across all Optum Global Solutions India

  • Diamond Recognition

    RADA, Optum Operations - United Health Group Company

    For helping provider engagement reporting team with pivoting huge datasets with Python programs and automate the whole process.

  • Ruby Award for Performance

    RADA, Optum Operations - United Health Group Company

    For supporting multiple Teams with developing automations and coding work

  • Special Expertise Award

    RADA, Optum Operations - United Health Group Company

    For helping in the transition of Technology Development Program Initiative and helping in the automation process with Python coding.

Test Scores

  • BITSAT

    Score: 279/450

  • Gitam University Entrance test - GAT

    Score: 212/300

    Secured a statewide rank of 105 in Andhra Pradesh (Before Bifurcation)

Languages

  • English

    Full professional proficiency

  • Telugu

    Professional working proficiency

  • Hindi

    Elementary proficiency

Recommendations received

1 person has recommended Vikas

Join now to view

View Vikas’ full profile

  • See who you know in common
  • Get introduced
  • Contact Vikas directly
Join to view full profile

Explore more posts

Explore top content on LinkedIn

Find curated posts and insights for relevant topics all in one place.

View top content

Add new skills with these courses

See all courses