Strwythura: construct an entity-resolved knowledge graph from structured data sources and unstructured content sources, implementing an ontology pipeline, plus context engineering for optimizing AI application outcomes within a specific domain. This produces a Streamlit app, with MLOps instrumentation.

This repository contains a notebook demonstrating a practical implementation of the so-called Entity Embedding for Encoding Categorical Features for Training a Neural Network.

Discover relevant information about categorical data with entity embeddings using Neural Networks (powered by Keras)

Entity Embedding with LSTM for Time Series

Connected Data London 2025 Masterclass: Combining Data from Structured and Unstructured Sources to create High-Quality Knowledge Graphs

This repo contains various data science strategy and machine learning models to deal with structure as well as unstructured data. It contains module on feature-preprocessing, feature-engineering, machine-learning-models, bayesian-parameter-tuning, etc, built using libraries such as scikit-learn, keras, h2o, xgboost, lightgbm, catboost, etc.

Semantics Driven Embedding Learning for Effective Entity Alignment, ICDE 2022

Deep Learning and Entity Embeddings to predict driving behaviour and cluster accident hotspots

Train word2vec and keeps all entities regardless of their frequency

A small library that can encode categorical variables to entity embeddings using a TensorFlow 2.0 neural network. Supports classification and regression problems. Network parameters are adjustable.

Kaggle Competition