Rajeev Gupta, Machine Learning Developer in Delhi, India
Rajeev Gupta

Machine Learning Developer in Delhi, India

Member since May 7, 2019
Rajeev is passionate about data and machine learning and has more than five years of experience in data science projects across numerous industries and applications. He's currently focused on cutting-edge technologies such as TensorFlow, Keras, deep learning, and most of the Python data science stack. Rajeev has used these skills to solve many real business problems in NLP, image processing, and time series domains.
Rajeev is now available for hire

Portfolio

Experience

Location

Delhi, India

Availability

Full-time

Preferred Environment

Google Cloud, Jupyter Notebook, Spyder, Git

The most amazing...

...project I've implemented was a NLP attention boosted sequential inference model to automate one of the business processes.

Employment

  • Independent Consultant — Data Scientist

    2017 - PRESENT
    JSS Information Technology Business Incubator
    • Associated with JSS Information Technology Business Incubator as a data science mentor.
    • Helped small companies and startups take advantage of their data.
    • Created predictive models using machine learning.
    • Worked with natural language processing with neural networks.
    • Developed classification and regression algorithms.
    • Implemented time-series forecasting.
    • Developed image detection with deep learning.
    Technologies: Google Cloud Platform (GCP), Git, Jupyter Notebook, Keras, TensorFlow, Scikit-learn, Python
  • Data Scientist

    2019 - 2019
    A Telecommunications and Media Company in the US
    • Worked with a telecommunications and media company in the US on identifying fake news.
    • Developed two models to identify sarcasm and quantification fallacies in articles.
    Technologies: PyTorch, TensorFlow, Python
  • Independent Consultant – Data Scientist

    2019 - 2019
    IBM
    • Worked for IBM US to optimize its US facility leases to run its operation.
    • Developed a Python model to improve facility utilization, reduce facility operations cost and reduce lease cost along with number of business constraints.
    Technologies: Linear Programming, Plotly, Python
  • Independent Consultant – Data Scientist

    2018 - 2018
    AbbVie, Inc.
    • Worked closely with the C-level executive and product management team to analyze the survey and produced data/reports.
    • Helped the product team and executive team to make more informed decisions—increasing market share through the identification of new opportunity, target segments and devising ingenious new ways of resolving constraints.
    Technologies: Association Rule Learning, Cluster, Regression, Matplotlib, Plotly, R, Python
  • Independent Consultant – Data Scientist

    2017 - 2018
    Newristics
    • Developed a Python app which uses natural language processing with deep neural networks sequence to sequence learning to automate business process.
    • Reduced the cost of business operations.
    Technologies: Google Cloud Platform (GCP), Git, Jupyter Notebook, Keras, TensorFlow, Scikit-learn, NLTK, SpaCy, GloVe, Gensim, LSTM, Python
  • Data Scientist

    2016 - 2017
    Sopra Steria Singapore
    • Worked with the Land Transport Authority, Singapore to implement the vision to convert the city into a digital and intelligent one to improve the efficiency of services for the citizens, using machine learning, predictive modeling, and data mining.
    Technologies: Git, Jupyter Notebook, Keras, TensorFlow, Scikit-learn, Tableau, Python
  • Data Scientist

    2014 - 2015
    Steria India
    • Built a recommendation system for an eCommerce site; it recommended the best possible items to buy based on customer history and collaborative filtering.
    • Helped with customer churn prediction by developing a classification algorithm for a retail bank to identify customers likely to churn balances in the next quarter by at least 50% vis-a-vis current quarter.
    • Created a classification algorithm for a retail bank to improve sales from existing customers by cross-selling one of its product, the personal loan (customer cross-sales).
    Technologies: Classification, Cluster, Regression, Matplotlib, Plotly, R, Python
  • Technical Program Manager

    1997 - 2014
    Steria India — Barclays Bank
    • Set up business benefits of around £43 million over five years in customer retention, cost savings, and new business opportunities at an estimated cost of around £12 million.
    • Acted as a vital member of the steering committee that identified user needs and developed customized solutions for around 250,000 Barclaycard acquiring merchants.
    • Led a project team of 147 members including solution architects, designers, developers, and testers spread across multi-geographical locations through the entire project development life cycle.
    • Consistently stayed within around 5% of resource and budget forecast monthly.
    • Recognized as problem solver within a team of 22 project managers in the portfolio of annual spend over £70 million.
    Technologies: Oracle, Content Management, Ab Initio, WebSphere, XML, Java, COBOL, JCL, Virtual Storage Access Method (VSAM), IBM DB2, CICS

Experience

  • IBM (Development)

    IBM US leases several facilities across the US to run its operation. The objective of this project was to improve facility utilization and reduce facility operations and lease costs, along with many business constraints.
    I developed the Python integer programming algorithm to solve this problem. Considering the business constraints made this problem interesting and unique. I parameterized the optimization period (the period to look into the future) in the algorithm to provide multiple solutions. The client especially appreciated this feature.
    Technologies: Python, Plotly, Linear Programming, Package Pulp

  • Newristics (Development)

    Newristics is a US-based global leader in applying decision-heuristic science to marketing. Using heuristic psychology (500+ different heuristics), it rewrites each marketing message.

    I automated the message scorer process where a team compares the new message against the old one and analyzes it to rate how closely it depicts the heuristic.

    Text data is then preprocessed with text cleaning, text normalization, and generated unigram bigram of normalized data. I built two main models to solve this problem: XGBoost and deep neural network seq-to-seq learning.

    For XGBoost, I created around 900 features (divided into three sections).
    • NLP basic features: count/ratio of words/character of the message, TF-IDF of unigram/bigram, gensim TF-IDF similarity, and so on
    • Word embedding—similarity of self/pre-trained Word2vec/GloVe-weighted average embedding vectors (TF-IDF as weight), etc.
    • Graph—degree of nodes, the intersection of neighbors, k-core/k-clique, degree of separation, etc.

    I used the deep learning seq-to-seq model to enhance the sequence inference neural network architecture.

    Technologies: Python, LSTM, gensim, GloVe, SpaCy, NLTK, Scikit-learn, TensorFlow, Keras, Jupyter Notebook, Git, Google Cloud Platform

  • AbbVie, Inc. (Development)

    AbbVie, Inc. is a leading pharmaceutical company and introduced a drug whose market share slipped from 65% to 49%. They conducted a physician survey on three themes to help in strategic planning.

    We interviewed 119 physicians about HCV regiment attributes which impact the market driver, 55 physicians concerning patient treatment, and 60 physicians about sales rep interaction and their impression about the message and interaction.
    I worked closely with the C-level executive and product management team to analyze the survey and produced data/reports. This helped the product team and executive team to make more informed decisions—increasing market share through the identification of new opportunity, target segments, and devising ingenious new ways of resolving constraints.
    Technologies: Python, R, Plotly, Matplotlib, Regression, Cluster, Association Rule

  • Classify H&E Stained Histological Breast Cancer Images (Development)

    I participated in a hackathon to classify H&E stained histological breast cancer images. We got a minimal set of training data (a few hundred images). To increase the robustness of the classifier, I used a strong data augmentation and deep convolutional feature extractor at different scales with pre-trained CNNs on ImageNet. On this feature set, I applied a highly accurate gradient boosting algorithm. I also avoided training neural networks on this amount of data to prevent suboptimal generalization.

    Technologies: Python 3, Keras, NumPy, Pandas, SciPy, Scikit-learn

  • Demand Forecast at an SKU-level for a Brewery Company (Development)

    Problem: They have a large portfolio of products distributed to retailers through wholesalers (agencies). There are thousands of unique wholesaler-SKU/product combinations.

    In order to plan its production and distribution as well as help wholesalers with their planning, it is important for them to have an accurate estimate of demand at SKU level (34) for each wholesaler (60).

    Data: Four years of data of 60 agencies and 34 SKUs are used for prediction.
    • Price sales promotion (dollar/hectoliter): The price, sales, and promotion in dollar value per hectoliter at an agency-SKU-month level
    • Historical volume (hectoliters): Sales data at an agency-SKU-month level
    • Weather (degree celsius): The average maximum temperature at an agency-month level
    • Industry soda sales (hectoliters): Industry-level soda sales
    • Event calendar: Event details (sports, carnivals, and so on)
    • Industry volume (hectoliters): Industry actual beer volume
    • Demographics: Demographic details (yearly income in dollars); used deep neural networks sequence to sequence learning for demand prediction

  • Satellite Imagery Feature Detection Using Deep Learning (Development)

    I developed a model for satellite imagery feature detection using deep learning. 1KM x 1KM satellite images are in both 3-band and 16-band formats. This multi-band imagery is taken from the multispectral (400-1040NM) and short-wave infrared (SWIR) (1195-2365NM) range.

Skills

  • Languages

    Python, Python 3, R, CICS, COBOL, Java, XML
  • Frameworks

    LightGBM
  • Libraries/APIs

    TensorFlow, TensorFlow Deep Learning Library (TFLearn), Matplotlib, Scikit-learn, Sklearn, Pandas, NumPy, XGBoost, CatBoost, Keras, PyTorch, SciPy, Dask, LSTM, SpaCy, NLTK
  • Tools

    Jupyter, GitHub, Seaborn, Plotly, Git, Spyder, Gensim, Cluster, Tableau, JCL, Ab Initio
  • Paradigms

    Data Science, Agile Software Development, Linear Programming
  • Platforms

    Docker, Jupyter Notebook, Google Cloud Platform (GCP), WebSphere, Oracle
  • Storage

    Data Pipelines, Google Cloud, IBM DB2, Virtual Storage Access Method (VSAM)
  • Other

    Data Analysis, Data Analytics, Data Scraping, Data Engineering, Mixed Integer Linear Programming, Deep Learning, Deep Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Long Short-term Memory, Natural Language Processing (NLP), Image Processing, Time Series Analysis, Artificial Intelligence (AI), Machine Learning, Numba, Optimization, Reinforcement Learning, Deep Reinforcement Learning, GloVe, Regression, Association Rule Learning, Classification, Content Management

Education

  • Master's degree in Computer Science
    1991 - 1994
    Jawaharlal Nehru University - New Delhi, India
  • Bachelor's degree in Mathematics
    1987 - 1990
    Delhi University - Delhi, India

To view more profiles

Join Toptal
Share it with others