Professional
summary
Completed a PGP in data science from Great Learning.
B.tech computers graduate Working with Intelytica as a machine learning specialist lead. Working on Invoice extraction project for a client.
Skills:
- Python
- Machine learning
- NLP
- Deep Learning
- Statistics
- Tableau
- Statistical modelling
- Predictive modelling
- Hypothesis testing
- R language
- SQL
- Text classification and Sentiment analysis
Professional summary
A total of 4 years of experience; 3 years as a business analyst and 1 year as a machine learning specialist
Business analyst at Aagama IT Biz Sols.
- Worked on various projects while my tenure here.
- Worked on an ecommerce project.
- Received going the extra-mile award.
Machine learning specialist at Intelytica
- Working on an Invoice extraction project where I've extracted text from different formats of files of invoices and make them a database table.
- Python
- NLP
- SQL
- Deep Learning
- LSTMs
- flask
Tools and techniques:
Academic projects
- AirDrive Preliminary survey report
- Description
- tools/skills
- Communities and their crime prediction
- Description
- tools/skills
- Dataset
- Customer segmentation using RFM analysis and clustering techniques
- Description
- tools/skills:
- Facial emotion detection>
- Description
- tools/skills:
- Recommender system
- Description
- tools/skills:
The survey report was about enquiring people’s interests on a medium of storage they use and if they would like to upgrade to cloud or HDD or both together.
Data visualization using Tableau, Excel.
Finding out the most important variables that best explains the total number of crimes per 100k population. Applying various regression models and choosing the best model that describes the data
Machine learning with python, EDA
Communities_crime . Source: UCI repository. Programming language: Python
Creating a customised marketing campaign, by segmenting customers into three different groups namely, Recency, Frequency and Monetary.
Machine learning with python, Excel, Exploratory Data Analysis.
Developed a facial emotion recognition algorithm. Trained the model extensively on 20k photos with 6 different emotions(happy, sad, disgust, neutral, sarcastic, surprised)spread across the dataset.
python, tensorflow, opencv.
A recommender system built on IMDB movies data set. It is a content based recommender system which will recommend your next movie based on the genres/content of the movies you've seen.
Python with NLP techniques