Bhavana Raghupatruni

Software Developer(AI)
Contact: 8184850022

E-Mail: [email protected]

3 Years of IT experience in historic data and apply statistical concepts to make cross-sectional
predictions. Predictive analytics uses many techniques from data mining, statistics, modelling, machine
learning, and artificial intelligence to analyse current data to make predictions about future.

PROFESSIONAL SYNOPSIS
SUMMARY:
 Experience using ML libraries, such as scikit learn, Seaborn, Matplotlib, Pandas, numpy,
RegEx etc.
 Experience diving into data to discover hidden patterns
 Take ownership of the data science model end-to-end from data collection to model building
to monitoring the model in production.
 Solid understanding of the mathematics related to data science probability, statistics, linear
algebra etc.
 Ability to understand business concerns and formulate them as technical problems that can
be solved using data and math / stats / ML
 Experience working as part of a product team, along with engineers and product managers,
to define the problem and execute the data science solution.
 Good interpersonal skills & learn new technologies and undertake challenges.

CORE COMPETENCIES
 Python Codes & Libraires like Numpy, pandas, Matplotlib, Seaborn, SciPy, RegEx etc.
 Machine learning algorithms for regression, classification, Clustering, Statistical modelling.
 API creation using Flask web Framework & Testing using Postman.
 Cloud: Aws, EC2, Sagemaker, Notebook instance, AWS container, S3
 Neural Networks, ANN, CNN, DNN, Transfer Learning, Back Propagation, Tensorflow 2.x, Keras
 SQL & MongoDB for Data Exploration and data analysis, CRUD operations, Subqueries, Window
functions, Joins
 Understanding, representation, classification & clustering of Text
Libraries: nltk, spacy, gensim, textblob, langdetect, googletrans
Techstat: BOW, TFIDF, word2vec, doc2vec, sent2vec, keypharse extraction
 Filter, Wrapper, Embedded Methods, P-Value, T-Test, Z-Test, ANNOVA test, Chi-Square Test, Info-Gain
Test,
Hypothesis Testing. Probability, statistics, linear algebra, probability, statistics, linear algebra, Gradient
Descent
 JIRA: Tickets, Tasks, Reports.
 HTML: Basic HTML page rendering
 GitHub: Git, Github, Gitbash
 Anaconda: Conda Env Setup.
 Methodology: Agile, Gira.
 Courses: Java Full Stack Development by Edubridge
Python by LUDIFU
Python by LinkedIn
ML by Udemy

PROFESSIONAL WORK EXPERIENCE

PROJECTS UNDERTAKEN
Project - 1
Project Name : Business Lending Solutions
Client : Santander Bank Corp, UK

Description:
Santander Bank Corporation is loan lending group is involved in the identification, structuring
and execution of transactions for its clients in diverse industries and geographies. consolidate credit
card debt, cover medical expenses, or make needed home improvements, a Santander Personal Loan
can help you get it done fast:.
Responsibilities
 Perform the full range of advanced analytics and visualization methodologies, techniques and
outputs associated with the area of expertise
 Extract, manipulate, analyse interpret data from various corporate data sources developing
advanced analytic solutions, deriving key observations, findings, insights, and formulating
actionable recommendations
 Generate clearly understood and intuitive advanced analytics outputs
 Participate in best practice sharing and communication platform for advancement of the data
analysis discipline
 Comply with established Service Level Agreements to ensure timely, high-quality deliverables
with value-add recommendations, clearly articulated key findings and observations

Project - 2
Project Name : Alfresco Document Classification system
Client : Alfresco , USA

Description:
Document management software from Alfresco lets one get content under control, with
seamless information governance and effective GDPR compliance that directly translates to tangible
business benefits. You can break down silos and enable productivity, anywhere, with a world-class
enterprise document management system. By classifying text, class can be assigned to each page of
the document. It involves Text-Pre-processing, Dynamic Language modelling, Natural Language
Processing.TF-IDF is used to find the features of intra-class documents. A statistical model is used to
find and differentiate the inter-class features. K-Nearest Neighbour, Support Vector Machine, Naïve
Bayes classifiers are used to classify the documents.

Responsibilities:
 Design, develop and implement analytical solutions using a variety of commercial and open
source tools (common tools include Python, R, TensorFlow).
 Develop and embed automated processes for predictive model validation, deployment, and
implementation.
 Connect and collaborate with subject matter experts in R&D, GIO-Q, Commercial and Medical.
 Make impactful contributions to internal discussions on emerging machine learning
methodologies.
 Educate the organization both from IT and the business perspectives on these new approaches,
such as testing hypotheses and statistical validation of results.

EDUCATION
 MCA - CSE -2017- JNTUH -76%
 BCS - CSE- 2015- JNTUH -70%
 HSC - 2011- BIE -84%
 SSC - 2009-SSC-70%

PERSONAL DETAILS

Birth Date : 05-08-1994