All Projects → nagadomi → Kaggle Coupon Purchase Prediction

nagadomi / Kaggle Coupon Purchase Prediction

Code for RECRUIT Challenge. 5th place.

Programming Languages

python
139335 projects - #7 most used programming language

Labels

Projects that are alternatives of or similar to Kaggle Coupon Purchase Prediction

Face Mask Detection
Face Mask Detection system based on computer vision and deep learning using OpenCV and Tensorflow/Keras
Stars: ✭ 774 (+1168.85%)
Mutual labels:  kaggle
Kaggle Web Traffic Time Series Forecasting
Solution to Kaggle - Web Traffic Time Series Forecasting
Stars: ✭ 29 (-52.46%)
Mutual labels:  kaggle
Bert Toxicity Classification
bert on Jigsaw Unintended Bias in Toxicity Classification
Stars: ✭ 46 (-24.59%)
Mutual labels:  kaggle
Deepfake Detection
DeepFake Detection: Detect the video is fake or not using InceptionResNetV2.
Stars: ✭ 23 (-62.3%)
Mutual labels:  kaggle
Pytorch Toolbelt
PyTorch extensions for fast R&D prototyping and Kaggle farming
Stars: ✭ 942 (+1444.26%)
Mutual labels:  kaggle
Machinelearningcourse
A collection of notebooks of my Machine Learning class written in python 3
Stars: ✭ 35 (-42.62%)
Mutual labels:  kaggle
Kaggle Quora Question Pairs
Kaggle:Quora Question Pairs, 4th/3396 (https://www.kaggle.com/c/quora-question-pairs)
Stars: ✭ 705 (+1055.74%)
Mutual labels:  kaggle
Fraud Detection
Credit Card Fraud Detection using ML: IEEE style paper + Jupyter Notebook
Stars: ✭ 58 (-4.92%)
Mutual labels:  kaggle
Kaggle Dae
kaggleのporto-seguro-safe-driver-prediction, michaelのsolver
Stars: ✭ 29 (-52.46%)
Mutual labels:  kaggle
Kaggle Ndsb
Code for National Data Science Bowl. 10th place.
Stars: ✭ 45 (-26.23%)
Mutual labels:  kaggle
4th Place Home Credit Default Risk
Codes and dashboards for 4th place solution for Kaggle's Home Credit Default Risk competition
Stars: ✭ 23 (-62.3%)
Mutual labels:  kaggle
Interview
Interview = 简历指南 + LeetCode + Kaggle
Stars: ✭ 7,207 (+11714.75%)
Mutual labels:  kaggle
Ml competition platform
Kaggle-like machine learning competition platform
Stars: ✭ 42 (-31.15%)
Mutual labels:  kaggle
Webinar Titanic
Stars: ✭ 16 (-73.77%)
Mutual labels:  kaggle
Lung Diseases Classifier
Diseases Detection from NIH Chest X-ray data
Stars: ✭ 52 (-14.75%)
Mutual labels:  kaggle
Entity Embedding Rossmann
Stars: ✭ 758 (+1142.62%)
Mutual labels:  kaggle
Healthcheck
Health Check ✔ is a Machine Learning Web Application made using Flask that can predict mainly three diseases i.e. Diabetes, Heart Disease, and Cancer.
Stars: ✭ 35 (-42.62%)
Mutual labels:  kaggle
Avito Duplicates Kaggle
Solution for Avito Duplicate Ads Detection competition
Stars: ✭ 58 (-4.92%)
Mutual labels:  kaggle
Data Science Bowl 2018
End-to-end one-class instance segmentation based on U-Net architecture for Data Science Bowl 2018 in Kaggle
Stars: ✭ 56 (-8.2%)
Mutual labels:  kaggle
Kaggle Seizure Prediction
solution for the American Epilepsy Society Seizure Prediction Challenge
Stars: ✭ 44 (-27.87%)
Mutual labels:  kaggle

Kaggle-Coupon-Purchase-Prediction

Code for Coupon Purchase Prediction (RECRUIT Challenge).

Note: This code is able to achieve a 5th place score (Private LB: 0.008776). But this is not a full version of my submitted solution (Private LB: 0.008905). My submitted solution is average of this solution and another XGBoost solution. This repositoy provides a simple version of 5th place solution.

Dependency (development environment)

  • OS: Ubuntu 14.04
  • Python: 2.7
  • pip: numpy(1.9), scipy, pandas, sklearn, sklearn-pandas, chainer

Data

Place the data files into a subfolder ./data. And unzip. (requires coupon_list_train.csv, coupon_list_test.csv, user_list.csv and coupon_detail_train.csv)

Local testing

validation-set: last 4 weeks.

$ python make_data.py --validation
$ python train.py --validation

Run

$ ./run.sh
$ ls -la submission_mlp.csv

It takes around 5 hours on 4 core CPU and 16GB RAM. If you get an out-of-memory error, use run_low_memory.sh.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].