created with

Profile photo

Harsh Praharaj

Machine Learning Engineer @ Quantiphi

Mumbai, India

Data Science enthusiast with interests in solving business problems, either through software development or data-driven insights.

Python SQL Time Series Forecasting Computer Vision NLP Pandas Tensorflow PyTorch Prophet Statsmodel


Project photo

Time Series Forecasting

Automated Cross-Validation Framework for Time Series Model Selection

Created an automated framework for a demand forecasting problem to choose the best-performing model on a weekly basis. The models considered are: Facebook Prophet Moving Average Simple Exponential Smoothing Holt Winter's ARIMA

Python ARIMA Prophet Pandas Matplotlib Data Wrangling EDA
Project photo

Computer Vision

Medical Segmentation

Developed a model to automate the detection of Tumour in a MRI. Implemented the encoder-decoder-based deep learning architecture:- U-NET with Adam optimizer. Optimized the model by converting it to a TFLite Model to reduce the latency.

Computer Vision Image Pre-Processing Tensorflow U-Net TF-Lite
Project photo

Image Classification

Plant Seedling Classification (Kaggle Competition)

Used pre-trained VGG16, ResNet50, and InceptionV3 networks to extract bottleneck features and build a model on top of each of them to evaluate and compare the model performances. (Model performances include classification report, confusion matrices, plots of Loss Vs Epochs) Optimized models using TF-Lite (Post Training Dynamic range quantization)

Transfer Learning Tensorflow Hyperparameter Tuning TensorRT TFF-Lite Data Visualization


Credit Card Default and LIME

Used tree-based algorithms (Decision tree, Random Forest, XGBoost) to determine whether a client will default or not. Explored LIME library and concepts like PD plots, local interpretation, surrogate models to explain the overall as well as instance-wise model performance.

Decision Trees Random Forest XGBoost sklearn LIME Pandas Data Visualization