Pinned Repositories
Akeed-Restaurant-Recommendation-Challenge
7th Place, The objective of this competition is to build a recommendation engine to predict what restaurants customers are most likely to order from given the customer location, restaurant information, and the customer order history. This solution will allow Akeed, an app-based food delivery service in Oman, to customise restaurant recommendations for each of their customers and ensure a more positive overall user experience. About Akeed (akeedapp.com):
Akeed-Restaurant-Recommendation-Challenge_getting_train-test
A quick notebook to get the train and test set.
KOWOPE
3rd Place. Kowope Mart is a Nigerian-based retail company with a vision to provide quality goods, education and automobile services to its customers at affordable price and reduce if not eradicate charges on card payments and increase customer satisfaction with credit rewards that can be used within the Mall. To achieve this, the company has partnered with DSBank on co-branded credit card with additional functionality such that customers can request for loan, pay for goods even with zero-balance and then pay back within an agreed period of time. This innovative strategy has increased sales for the company. However, there has been recent cases of credit defaults and Kowope Mart will like to have a system that profiles customers who are worthy of the card with minimum if not zero risk of defaulting. You have been employed as a Data Scientist to leverage Machine learning to predict customers who are likely to default or not. This is Qualification Competition for the Data Science Nigeria AI Bootcamp.
Lerato
A Retrieval based bot that responds to basic question about Zindi Africa- using cosine similarity between words entered by the user and the words in the corpus. We 'll define a function response which searches the user’s utterance for one or more known keywords and returns one of several possible responses. If it doesn’t find the input matching any of the keywords, it returns a response:” I am so sorry! I dont understand your words"
PRJ1-Flower_Breed-Analytics
To build a model that will help predict the flowers breed correctly for production purposes. this solution will help ABC to reduce cost, time and resources.
Product-Recommendation--ALS--FlaskApp
Machine Learning Product recommendation as an API & as a WEB app
Standard-Bank-Tech-Impact-Challenge
3rd Place, Predict the likelihood of credit default of ecommerce clients
Taxi_MLOps
Operationalizing Machine Learning models using TLC Trip Record Data
Urban-Air-Pollution-Challenge-by-ZindiWeekendz
You may have seen recent news articles stating that air quality has improved due to COVID-19. This is true for some locations, but as always the truth is a little more complicated. In parts of many African cities, air quality seems to be getting worse as more people stay at home. For this challenge we’ll be digging deeper into the data, finding ways to track air quality and how it is changing, even in places without ground-based sensors. This information will be especially useful in the face of the current crisis, since poor air quality makes a respiratory disease like COVID-19 more dangerous. We’ve collected weather data and daily observations from the Sentinel 5P satellite tracking various pollutants in the atmosphere. Your goal is to use this information to predict PM2.5 particulate matter concentration (a common measure of air quality that normally requires ground-based sensors to measure) every day for each city. The data covers the last three months, spanning hundreds of cities across the globe.
Zimnat-Insurance-Recommendation-Challenge
Sample data preparation on insurance recommendation challenge
abofficial444's Repositories
abofficial444/Zimnat-Insurance-Recommendation-Challenge
Sample data preparation on insurance recommendation challenge
abofficial444/Lerato
A Retrieval based bot that responds to basic question about Zindi Africa- using cosine similarity between words entered by the user and the words in the corpus. We 'll define a function response which searches the user’s utterance for one or more known keywords and returns one of several possible responses. If it doesn’t find the input matching any of the keywords, it returns a response:” I am so sorry! I dont understand your words"
abofficial444/Urban-Air-Pollution-Challenge-by-ZindiWeekendz
You may have seen recent news articles stating that air quality has improved due to COVID-19. This is true for some locations, but as always the truth is a little more complicated. In parts of many African cities, air quality seems to be getting worse as more people stay at home. For this challenge we’ll be digging deeper into the data, finding ways to track air quality and how it is changing, even in places without ground-based sensors. This information will be especially useful in the face of the current crisis, since poor air quality makes a respiratory disease like COVID-19 more dangerous. We’ve collected weather data and daily observations from the Sentinel 5P satellite tracking various pollutants in the atmosphere. Your goal is to use this information to predict PM2.5 particulate matter concentration (a common measure of air quality that normally requires ground-based sensors to measure) every day for each city. The data covers the last three months, spanning hundreds of cities across the globe.
abofficial444/Food-Assessment-Quality
Problem Description The food inspection department conducts regular inspection on food quality for various restaurants in the city. It’s a very well documented procedure and over time some good amount of data has been generated out of these inspections. The inspection department would like to predict where they should focus most in terms of their next inspection schedule, so that they can most optimize their time at hand to catch the worst offenders. Can the past inspection or any data that they have collected predict which facility will pass or fail. In this hackathon, MachineHack provides you with a subset of this dataset with information on food quality checks conducted on thousands of facilities that serve food across multiple cities. Your objective as a Data Scientist is to predict whether a facility will pass or fail the inspection based on a number of factors.
abofficial444/2019-Data-Science-Bowl
484th/3497th Top 14%; Competitors are challenged to predict scores on in-game assessments and create an algorithm that will lead to better-designed games and improved learning outcomes.
abofficial444/Data-Science-2019-AXA-MANSARD-INSURANCE
A Supervised learning problem to predict the probability of a insuring a building
abofficial444/ensemble-methods-notebooks
A collection of companion Jupyter notebooks for Ensemble Methods for Machine Learning (Manning, 2020)
abofficial444/java_developers
Series of core java programming project
abofficial444/MachineHack-Food-Quality
1st place solution to Food Quality Inspection Check Hackathon conducted by MachineHack
abofficial444/ProHack
Aliens problem solved using Machine Learning and Operation Research challenge
abofficial444/Uber-Movement-SANRAL-Cape-Town-Challenge
Unofficial 6th place solution; The aim of this challenge is to forecast if an incident will occur for each hour of each day per 500m road segment along the major roadways in Cape Town for 1 January 2019 to 31 March 2019
abofficial444/USAID-s-Intelligent-Forecasting-Challenge-Model-Future-Contraceptive-Use
2nd/120th... Greater access to contraceptives enables couples and individuals to determine whether, when, and how often to have children. Contraceptive access is vital to safe motherhood, healthy families, and prosperous communities. In low- and middle-income countries (LMIC) around the world, health systems are often unable to accurately predict the quantity of contraceptives necessary for each health service delivery site, in part due to insufficient data, limited staff capacity, and inadequate systems. When too few supplies are ordered, service delivery sites may run out, limiting access to contraceptives and family planning. When too much product is ordered, it leads to unused contraceptives that are wasted if they are left to expire. Accurate forecasting of contraceptive consumption can save lives, money, and time by ensuring health service delivery sites have what they need when they need it and by reducing waste in the supply chain. USAID works with local health care authorities and partners to support voluntary family planning and reproductive health programs in nearly 40 countries across the globe, which includes ensuring that contraceptives are available and accessible to people who need them. With this competition, USAID seeks to identify and test more accurate methods of predicting future contraceptive use at health service delivery sites.
abofficial444/AI4D-Predict-the-Global-Spread-of-COVID-19
8th place... The objective of this challenge is to build an epidemiological model that predicts the spread of COVID-19 throughout the world. The target variable is the cumulative number of deaths caused by COVID-19 in each country by each date. We have selected the cumulative number of fatalities rather than the number of reported infections as the target variable because the real number of infections is unknown and will perhaps never be known. The number of reported cases is understood to be underestimated and largely biased by the availability of tests, which varies from location to location and country to country. We encourage participants to engage with the literature available on approaches and considerations when modelling the spread of diseases. For this competition, we have used the publicly-available data from the Coronavirus COVID-19 Global Cases by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University (JHU), which is updated on a daily-basis.
abofficial444/Basic-Needs-Basic-Rights-Kenya-Tech4Mental-Health
Around 1 in 4 people will experience a mental health problem this year. Low-income countries have an estimated treatment gap of 85% (as compared with high-income countries with a gap of 35% to 50%). While Kenya has a mental illness prevalence rate that is comparable to that of high-income countries, there are still less than 500 healthcare professionals serving the country. In Kenya, there are growing concerns about mental health among young people, particularly university students that face a challenging and unique conflation of stressors that put them at risk of challenges like depression and substance abuse. From the use of app-based solutions for screening to electronically delivered therapies, the use of technologies including machine learning and AI will potentially transform the delivery of mental health services in the coming years. The objective of this challenge is to develop a machine learning model that classifies statements and questions expressed by university students in Kenya when speaking about the mental health challenges they struggle with. The four categories are depression, suicide, alchoholism, and drug abuse. This solution will be used for a prototype of a mental health chatbot designed specifically for university students. This initiative is a first step in leveraging technology to make mental health services more accessible and more user-friendly for young people in Kenya and around the world
abofficial444/causal_inference_python_code
Python code for part 2 of the book Causal Inference: What If, by Miguel Hernán and James Robins
abofficial444/Data-Analysis
Data Science Using Python
abofficial444/data-engineer-roadmap
Learning from multiple companies in Silicon Valley. Netflix, Facebook, Google, Startups
abofficial444/Forcasting-Weekly-Sales
A time series prediction; Forcasting Weekly Sales of a supermarket products
abofficial444/HABERMANS-SURVIVAL-DATASET
You may have to create a Kaggle account to donwload data. (https://www.kaggle.com/gilsousa/habermans-survival-data-set) 2.Perform a similar alanlaysis as above on this dataset with the following sections: 3.High level statistics of the dataset: number of points, numer of features, number of classes, data-points per class. 4.Explain our objective. 5.Perform Univaraite analysis(PDF, CDF, Boxplot, Voilin plots) to understand which features are useful towards classification. 6.Perform Bi-variate analysis (scatter plots, pair-plots) to see if combinations of features are useful in classfication. 7.Write your observations in english as crisply and unambigously as possible. Always quantify your results.
abofficial444/Predicting-reservation-cancellations-Predict-whether-resort-city-hotel-reservations-will-be-cancell
2nd place Analysis & Modelling... Customers cancelling reservations severely impact the results of hotels and dining facilities. It not only damages revenue, but also wastes the food in stock and personnel expenses used to provide services. The goal of this competition is to use data consisting of over 100,000 reservations to categorize reservations into those that will and will not be cancelled. The data uses actual reservations that were made in several cities across Portugal. This is a challenge that predicts cancellations. It’s also very meaningful for society because it can later be used for various purposes such as analyzing the causes behind the cancellations. Since the data is in chronological order, you will be able to learn data processing methods that can be applied in various fields.
abofficial444/Scooters-Challenge
3rd/20th; A predictive model to predict who is likely to buy the yet to release scooter products based on their past sales record
abofficial444/Sea-Turtle-Rescue-Forecast-Challenge
9th place solution / 96th ; The objective of this competition is to create a machine learning model to help Kenyan non-profit organization Local Ocean Conservation anticipate the number of turtles they will rescue from each of their rescue sites as part of their By-Catch Release Programme.
abofficial444/Spot-the-Mask-Challenge-by-ZindiWeekendz
Face masks have become a common public sight in the last few months. The Centers for Disease Control (CDC) recently advised the use of simple cloth face coverings to slow the spread of the virus and help people who may have the virus and do not know it from transmitting it to others. Wearing masks is broadly recognised as critical to reducing community transmission and limiting touching of the face. In a time of concerns about slowing the transmission of COVID-19, increased surveillance combined with AI solutions can improve monitoring and reduce the human effort needed to limit the spread of this disease. The objective of this challenge is to create an image classification machine learning model to accurately predict the likelihood that an image contains a person wearing a face mask, or not. The total dataset contains 1,800+ images of people either wearing masks or not. Your machine learning solution will help policymakers, law enforcement, hospitals, and even commercial businesses ensure that masks are being worn appropriately in public. These solutions can help in the battle to reduce community transmission of COVID-19.
abofficial444/The-Zimnat-Insurance-Assurance-Challenge-by-ZindiWeekendz
During a crisis like COVID-19, we recognize the crucial role that insurance can play in our ability to weather an unexpected storm. Insurance products help people and their families access the financial and medical support they need when they need the help the most. Insurance companies rely on monthly premiums from their clients as their principal source of income; these premiums buy the client insurance against accidents, fires, injury or theft. However, insurance is a competitive market, and there are many factors that can cause a customer to leave an insurance provider, be it poor service delivery, competitive pricing, personal financial stress such, or other environmental factors. This customer loss is known in the business as ‘churn’. In this hackathon your objective is to develop a predictive model that determines the likelihood for an insurance customer to churn - to seek an alternative insurer or simply drop out of the insurance market altogether. In light of the current pandemic, churn prediction can be used to offer targeted support and tailored services to certain customers vulnerable to churning. This means more people can continue to be covered when they most need it most and insurance companies can be more efficient at serving and retaining their customers.
abofficial444/TimeSeriesAnalysisForMachineLearning
Complete machine learning pipeline for time series analysis
abofficial444/Transformers_Tuto
abofficial444/UNICEF-Arm-2030-Vision-1-Flood-Prediction-in-Malawi
12th/492nd, On 14 March 2019, tropical Cyclone Idai made landfall at the port of Beira, Mozambique, before moving across the region. Millions of people in Malawi, Mozambique and Zimbabwe have been affected by what is the worst natural disaster to hit southern Africa in at least two decades. In recent decades, countries across Africa have experienced an increase in the frequency and severity of floods. Malawi has been hit with major floods in 2015 and again in 2019. In fact, between 1946 and 2013, floods accounted for 48% of major disasters in Malawi. The Lower Shire Valley in southern Malawi, bordering Mozambique, composed of Chikwawa and Nsanje Districts is the area most prone to flooding. The objective of this challenge is to build a machine learning model that helps predict the location and extent of floods in southern Malawi. This competition is sponsored by Arm and UNICEF as part of the 2030 Vision initiative.
abofficial444/Who-wins-the-Big-Game
9th place solution / 98th ; A sports betting firm has utilized the data augmentation technique to synthesize a data set of championship outcome of the Big Game's participants and other data. Your task is to generate a model to determine and classify whether a given team will win the championship or not.
abofficial444/WIDS-Datathon-2020
175th/951st Top 19%; The challenge is to create a model that uses data from the first 24 hours of intensive care to predict patient survival. MIT's GOSSIS community initiative, with privacy certification from the Harvard Privacy Lab, has provided a dataset of more than 130,000 hospital Intensive Care Unit (ICU) visits from patients, spanning a one-year timeframe. This data is part of a growing global effort and consortium spanning Argentina, Australia, New Zealand, Sri Lanka, Brazil, and more than 200 hospitals in the United States.
abofficial444/Womxn-in-Big-Data-South-Africa
17th/199th; Female-Headed Households in South Africa prediction challenge