All Projects → yaoleiliu → 2017 Jdd Global Data Explorer Competition

yaoleiliu / 2017 Jdd Global Data Explorer Competition

2017京东金融全球数据探索者大赛(3rd place)

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to 2017 Jdd Global Data Explorer Competition

Bee University
Project thu thập điểm chuẩn đại học 2014 - 2018 và phân tích dữ liệu
Stars: ✭ 73 (-29.81%)
Mutual labels:  data-mining
Dc Hi guides
[Data Castle 算法竞赛] 精品旅行服务成单预测 final rank 11
Stars: ✭ 83 (-20.19%)
Mutual labels:  data-mining
Papers Literature Ml Dl Rl Ai
Highly cited and useful papers related to machine learning, deep learning, AI, game theory, reinforcement learning
Stars: ✭ 1,341 (+1189.42%)
Mutual labels:  data-mining
Tsrepr
TSrepr: R package for time series representations
Stars: ✭ 75 (-27.88%)
Mutual labels:  data-mining
E Maxx Eng
Translation of http://e-maxx.ru into English
Stars: ✭ 1,238 (+1090.38%)
Mutual labels:  algorithm-competitions
Acm Icpc Algorithms
Algorithms used in Competitive Programming
Stars: ✭ 1,281 (+1131.73%)
Mutual labels:  algorithm-competitions
Ffbe
Datamining for FFBE GL
Stars: ✭ 69 (-33.65%)
Mutual labels:  data-mining
Gitlogg
💾 🧮 🤯 Parse the 'git log' of multiple repos to 'JSON'
Stars: ✭ 102 (-1.92%)
Mutual labels:  data-mining
C
Collection of various algorithms in mathematics, machine learning, computer science, physics, etc implemented in C for educational purposes.
Stars: ✭ 11,897 (+11339.42%)
Mutual labels:  algorithm-competitions
Msnoise
A Python Package for Monitoring Seismic Velocity Changes using Ambient Seismic Noise | http://www.msnoise.org
Stars: ✭ 94 (-9.62%)
Mutual labels:  data-mining
Tsv Utils
eBay's TSV Utilities: Command line tools for large, tabular data files. Filtering, statistics, sampling, joins and more.
Stars: ✭ 1,215 (+1068.27%)
Mutual labels:  data-mining
Dex
Dex : The Data Explorer -- A data visualization tool written in Java/Groovy/JavaFX capable of powerful ETL and publishing web visualizations.
Stars: ✭ 1,238 (+1090.38%)
Mutual labels:  data-mining
Vvedenie Mashinnoe Obuchenie
📝 Подборка ресурсов по машинному обучению
Stars: ✭ 1,282 (+1132.69%)
Mutual labels:  data-mining
Rental Prediction
2018年全国大学生计算机应用能力大赛之住房月租金预测第一名代码
Stars: ✭ 74 (-28.85%)
Mutual labels:  data-mining
Graph sampling
Graph Sampling is a python package containing various approaches which samples the original graph according to different sample sizes.
Stars: ✭ 99 (-4.81%)
Mutual labels:  data-mining
Bolt
Fast approximate vector operations
Stars: ✭ 70 (-32.69%)
Mutual labels:  data-mining
Csmath 2020
This mathematics course is taught for the first year Ph.D. students of computer science and related areas @ZJU
Stars: ✭ 85 (-18.27%)
Mutual labels:  data-mining
Gspan
Python implementation of frequent subgraph mining algorithm gSpan. Directed graphs are supported.
Stars: ✭ 103 (-0.96%)
Mutual labels:  data-mining
Vizuka
Explore high-dimensional datasets and how your algo handles specific regions.
Stars: ✭ 100 (-3.85%)
Mutual labels:  data-mining
Daggy
Daggy - Data Aggregation Utility. Open source, free, cross-platform, server-less, useful utility for remote or local data aggregation and streaming
Stars: ✭ 91 (-12.5%)
Mutual labels:  data-mining

2017京东金融全球数据探索者大赛(3th place)

本次大赛一共有四个赛题,我做的的是登录行为识别赛题。成绩为A榜第一,B榜第三。

团队介绍

团队名称:jd_156192rqk。 成员分别来自西安电子科技大学(队友)和四川大学(我)。

代码运行环境

  • pandas

  • numpy

  • sklearn

  • xgboost

  • python2.7

  • 程序入口:sh run.sh

解决方案

登录行为识别赛题主要是根据登录行为来判断本次交易是否是危险交易。我们的方案主要是通过刻画id画像、ip画像和dev画像的思路来构造特征,然后分别用xgboost、LR来预测, 取两个模型中风险最大的top200,对这200个进行交集运算。对于某次交易,如果xgboost和LR模型同时预测为危险交易,则判定该次交易为危险交易;否则为正常交易。特征构造 可参见代码,里面有详细的注释。

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].