-
The University of Edinburgh
- Nairobi, Kenya
- kennedykwangari@gmail.com
- @kennedykwangari
- https://kennedykwangari.github.io/
- kennedykwangari
- kennedykwangari
Highlights
-
-
-
In this challenge we have given a directed social graph, and we have to predict missing links to recommend users (Link Prediction in graph)
-
-
<
8000
div class="col-10 col-lg-9 d-inline-block">
Detecting-Fake-News- Public
Building algorithms that detect fake news using collected data from different articles
This repository contains my full work and notes on Coursera's NLP Specialization (Natural Language Processing) taught by the instructor Younes Bensouda Mourri and Łukasz Kaiser offered by deeplearn…
Collection of beautiful, performant data web-apps built using the Streamlit’s open-source app framework
Extracting human-understandable insights from any machine learning model. Exploring various MLI (Machine Learning Interpretability) techniques that help us debug, decode, get good accuracy and expl…
Building a Friendly-robotic personal assistant Chatbot with Long Short Term Memory
Aspect-based Sentiment Analysis
This repository contains data sets and code snippets on how to process, classify, cluster, summarize, understand syntax, semantics and sentiment of text data with the power of Python!.
The aim of the project is to provide a reference container guide of the numerous broad topics in the field of Time Series Analysis.
This dataset comprises of sales transactions captured at a retail store. We should predict How much will a customer spend?. The purchase amounts
Leveraging on Unsupervised Learning Techniques (K-Means and Hierarchical Clustering Implementation) to Perform Market Basket Analysis: Implementing Customer Segmentation Concepts to score a custome…
We are tasked to Perform Cohort and Recency Frequency and Monetary Value Analysis to understand the value derived from different customer segments. Further, we will divide customers in different cl…
A quick walkthrough an Automl framework called H2O AutoML and provides easy way to run multiple models and help pick the top ones along with its hyperparameter. It also gives an model deployment co…
Developing an NLP Model in Python and Deploying it on Flask that classifies the message as "spam" or "ham.
This repository contains Deep Learning Projects worked on: Tensorflow and Keras Deep Learning Projects Implementations
Tasked to automatically suggest a product price to online sellers based on information a user provides for the product listing: The Mercari Price Suggestion Challenge
Tasked to build a Recommendation Engine that suggests new products to increase sales and dictate trends.
We were tasked to build a state-of the art deep learning model that seeks to inform, support and accelerate Wildlife Conservation and Ecological Research in the Serengeti National Park in Tanzania.
Using data from Taarifa and the Tanzanian Ministry of Water, can you predict which pumps are functional, which need some repairs, and which don't work at all? https://www.drivendata.org/competition…
Predict whether the cancer is benign or malignant. https://www.kaggle.com/uciml/breast-cancer-wisconsin-data
Can you predict how capable each applicant is of repaying a loan? https://www.kaggle.com/c/home-credit-default-risk
Anonymized credit card transactions labeled as fraudulent or genuine: https://www.kaggle.com/mlg-ulb/creditcardfraud
Forecast use of a city bike share system
Financial Inclusion remains one of the main obstacles to economic and human development in Africa. For example, across Kenya, Rwanda, Tanzania, and Uganda only 9.1 million adults (or 13.9% of the a…
This dataset includes customers who have paid off their loans or not: This competition was hosted at Kaggle on https://www.kaggle.com/zhijinzhai/loandata