Printing tool Download PDF


Naga Indukur is a System Engineer with 2 years of professional experience in Software Industry. He is very much interested to apply Machine Learning models in real time scenarios. Have worked on few projects like review classification, recommendation system for e-commerce websites.

Work experience


System Engineer

Tata Consultancy Services Ltd

Email Classification

Sapiem receives numerous mails from during interaction with clients as well as customers. To classify these emails, we have built a Machine Learning model as per requirement.

  • TF-IDF based word embedding is used to process text data
  • Emails are classified by Naive Bayes / SVM(Support Vector Machines) algorithm
  • created a REST API using FLASK and hosted these models in local machine.

Document Comparison

Bank of America receives several legal documents which comprises of updated agreement terms. Finding the difference between the old and new version of agreement is a tedious job. By using ML and NLP we automated the task of finding differences between two files.

  • Received legal documents are in pdf format, thus we extract the data into text format.
  • Using NLP, we compare two sets of data page by page.
  • Any change in both the files are highlighted and returned as an image.
  • Created a REST API using FLASK and hosted this model on Azure cloud.

Other taskes
  • Developed KPI (Key Performance Indicators) Reports to the client as per their requirements. Extracted, analysed and identified the parameters which hampers the performance/efficiency of the project.
  • Working on developing a semantic search based chatbot by integrating Lucene's solr and Word2Vec algorithm.

Highest Education

Jul 2012Apr 2016

Bachelor's of Technology (B.Tech)

GITAM University

Bachelor Of Technology, Electronics and Communication                    Score: 8.66


Sentiment Analyser

Using Python, ML, NLP, Twitter

Twitter has huge amount of text data. We extract data from twitter using data mining techniques like tweepy, and pre process the data using regex. By using various libraries like Textblob, Vander Sentiment Analyser we find the type of sentiment for each of the tweet posted by an user. 

Airbnb Destination predictor

Using Python and ML Algorithms

This project analyzed an imbalanced dataset. With proper Exploratory data analysis, data was cleaned and observed it was imbalanced. Thus, by balancing the data we found efficiency in multiple ML algorithms like Logistic regression, Naïve Bayes theorem, random forest and finally predicted the output with the best model.

Review Classifier

Using Python, NLP and NLTK

From a wide range of reviews received by a restaurant, by using Python libraries and NLP technologies we classified whether a provided review was positive or negative.