Anand Raj | Software Developer

Hi, I'm Anand Raj.

A

Experienced and focused engineer with good coding skills and a background in professional software engineering. Driven by a passion for data and a strong desire to explore machine learning and sophisticated analytics, I aim to contribute to the company's advancement while also fostering personal growth.

About

I am currently pursuing a graduate degree in Data Science at George Washington University(expected graduation - May 2025). I take pleasure in collaborating with like-minded individuals who share similar interests, as it allows for the development of both personal and professional skills within the peer. I am looking for a dynamic role that challenges me to utilize my Software Engineering skills, providing chances for professional growth, exciting experiences, and personal development.

Programming languages: R, Python, and C.
Database: SQL, MongoDB, and Neo4j (Graph Database).
Machine Learning Algorithms: Linear/Logistic/Lasso/Ridge Regression, Decision Trees, Naive Bayes, KNN, Random Forest, Stacking, SVM, XGBM, Bagging Methods, Cascading Classifiers.
Data Mining: PCA, t-SNE, Recommendation Systems & Matrix Factorization, and Clustering - K Means, Hierarchical, DBSCAN.
Time series analysis/Forecasting: AR, ARMA, ARIMA, and SARIMA.
Deep Learning: Artificial Neural Networks, Convolutional Neural Networks, Multilayer Perceptron, Long Short Term Memory(LSTM), Recurrent Neural Network(RNN) and Generative adversarial networks(GAN).
Product Development: Agile Methodology, Product Life Cycle, JIRA for Ticketing, Git, GitHub.
Others: Tableau, Flask, AWS EC-2, Streamlit and Heroku.

Experience

AARP

Data Science Intern

Processed and cleaned 28,000 articles to analyze customer behaviour, utilizing Databricks for data ingestion, HTML parsing and data cleaning.
Developed a dynamic labelling system using LLMs, iteratively generating new labels for articles based on previous batches, resulting in a 90% reduction in manual labelling efforts.
Conducted linguistic validation on 500 randomly selected articles to ensure accurate labelling and continuously improved labelling accuracy by refining LLM prompts.
Automated customer query resolution by fine-tuning a T5 model on 34,000 customer queries and resolutions, applying Parameter Efficient Fine Tuning(PEFT) to optimize model performance.
Optimized a query resolution model, leading to a 60% reduction in the customer care team's workload by improving response accuracy and efficiency.
Engaged in ongoing work to generate personalized marketing messages for 10 million customers, leveraging customer attributes to deliver highly targeted content and enhance marketing effectiveness.

Jun 2024 - Till date | Washington DC, USA

Continental AG

Software Engineer

Worked on Advanced Driving Assistance Systems and developed products like Emergency Brake Assist, and Rear Pre-Crash Predict. Major products: Volkswagen ID Buzz and Mercedes Benz Sprinter Van.
Developed algorithm using C. Implemented automation using Python scripting.
Provided problem-solving solutions to customer-reported problems in the simulation environment.
Delivered better performance with just 2 false positives per 10,000 kilometers, optimizing key performance indicators.
Skills learnt: Development in C, Python for scripting, Git, GTest for Testing, QAC for Quality, JIRA for ticketing, Product Development, Agile Methodologies, ASPICE.

Sep 2021 - Aug 2023 | Bangalore, India | Total experience - 2 years

Innodatatics

Data Science Intern

Collaborated with a dynamic team to conduct in-depth data analysis utilizing Python and Tableau, providing valuable insights into client's sales data. Analyzed user behavior, temporal trends, and distinctions between free and paid users.
Formulated data-driven recommendations and compelling narratives and communicated to our client
Skills learnt:Python, Data Analysis, ML Modelling, Flask.

Jun 2020 - Aug 2020 | Bangalore, India | Total experience - 3 months

Defense Research Development Organization (DRDO)

Intern

Worked on validation and verification process standards in avionics hardware.
Collaborating with different teams and Reviewing standards of all the Validation and verification processes.
Skills learnt: DO-254 and DAL-C Certification of Hardware.

Jan 2020 - Feb 2020 | Bangalore, India | Total experience - 2 months

Projects

                
 EzFlow.ai Platform 
                  User-friendly software product designed to democratize machine learning.
                
AccomplishmentsTools: Python, Flask, HTML and CSS.
Leading the development of EzFlow.ai, a user-friendly platform designed to empower users with no coding experience to learn and implement machine learning projects. 
By automating data preprocessing, model training, and result visualization, EzFlow.ai provides users with predictions and comprehensive summary reports.

Quora question pair similarity
                  Aims to identify duplicate questions using natural language processing
                
AccomplishmentsTools: Python, Flask, HTML and CSS. 
 Applied Natural Language Processing techniques to determine if two questions have similar meaning. 
 Performed comprehensive data analysis, feature engineering, and text data featurization to develop a predictive model.

New York City Taxi Trip Duration
                  To predict the total ride duration of taxi trips in New York city
                
AccomplishmentsTools: Python 
Developed a model for predicting trip duration using New York City pick-up and drop-off coordinates, involving 
                   extensive data cleaning, analysis, and training various ML models, achieving the lowest RMSE of 224 seconds.

Sentiment Prediction from Amazon reviews
                  Employs advanced NLP and ML to analyze Amazon reviews
                
AccomplishmentsTools: Python, Flask, AWS-for deployment.
Developed a model to predict if a text review of a product given by user is positive or negative
Performed extensive text cleaning and featurizing text data, achieved an AUC score of 0.90 using SGD Classifier. 
Deployed using Flask on AWS EC-2 virtual machine. 

Artificial Music Generator                  
                  Model to Generate music using LSTM neural networks.
                
AccomplishmentsTools: Python, Keras, Tensorflow 
Implements an Artificial Music Generator using LSTM (Long Short-Term Memory) networks, a type of recurrent neural network (RNN).
The system generates music character by character based on a given input dataset.
 LSTM model is trained on a corpus of music data and then sampled from the trained model to generate new music compositions.

University Recommendation System using Neo4j
                  A recommendation system for Recommending Similar Universities
                
AccomplishmentsTools: Neo4j, Flask.
NEO4J's graph database reimagines higher education by enabling highly personalized, 
                    context-aware university recommendations, transforming the educational landscape.

Research Publications

Facial Emotion Analysis

Facial Feature Extraction and Emotional Analysis Using ML

Accomplishments

Challenges in facial expression recognition.
Introduction of a deep learning approach with Convolutional Neural Networks(CNN).
Emphasis on CNNs' role in feature learning for emotion detection.
Click on the link to view the research paper for detailed information.

Prediction Algorithm evaluation

Performance Comparison of Prediction Algorithms for Forecasting of Wind Power Generation

Accomplishments

Research compares ARIMA, SARIMAX, and ARMA algorithms for Wind power generation forecasting.
ARIMA identified as the most accurate with the lowest MSE (523.01).
Accurate forecasting minimizes errors, enhances power grid reliability.
Click on the link to view the IEEE paper for detailed information.