easunlu Goto Github PK

2017-ccf-bdci-enterprise

2017-CCF-BDCI-企业经营退出风险预测：9th/569 (Top 1.58%)

2017-ccf-bdci-enterprise-1

2017-CCF-BDCI-企业经营退出风险预测 复赛9th/569 (Top 1.58%)

2018-tiancheng

甜橙金融杯Rank14

2019-taida-jdata-top3

audit-ai

这个 repository 用以存放企业内审深度学习的代码和经过信息安全转化转化了的学习数据以及预测数据，将包括多个项目与每个项目里的多个版本。

awesome-data-comp-solution

数据科学/人工智能比赛解决方案汇总

b2b_customer_segmentation

bank-churn-model

银行客户流失预警模型

bankruptcy-prediction-growth-modelling

bdci-2018-supply-chain-demand-forecast

初赛Rank1 复赛Rank1 2018 CCF 大数据与计算智能大赛 供应链需求预测 Miracccccccle

ccxboost

中诚信xgboost模型自动化封装

clustering-analysis-in-python

This is a clustering analysis for a B2B travel company. The exploratory analysis was done in a different document. This code picks up after the features are selected/engineered and the file size is reduced.

customer_segmentation

Analysing the content of an E-commerce database that contains list of purchases. Based on the analysis, I develop a model that allows to anticipate the purchases that will be made by a new customer, during the following year from its first purchase.

data-sci-int-capstone

Assessing risk ratings from insurance client data

datadriven-customer-segmentation-with-python

generalized code used in my master thesis

debtdefaultresearch

对截止至2017年7月17日的债券违约事件进行梳理归因，并寻找宏观流动性影响因素，组成数据集。运用Lasso回归进行特征提取后，输入带L2惩罚项LR、SVM、NN、GBDT、RF等机器学习模型进行违约预测，得出GBDT预测效果最好以及特征工程对线性模型预测效果具有重要性的结论。

deepnude_nowatermark_withmodel

DeepNude source code，without watermark，with demo and model download link，one command to run offline，GAN/Pytorch/pic2pic

dockerfiles

Various Dockerfiles I use on the desktop and on servers.

duneanalytics

Unofficial Python Library for Dune Analytics

ec-churn-prediction-challenge

ENGIE Entreprises & Collectivités is a gas and power supplier for the French B2B market (businesses and local communities). French B2B market is about 160 TWh gas and 180 TWhpower. Our clients are segmented in two parts: large accounts on the one side, and middle-market on the other side. Since the end of gas and power regulated tariffs, our competitors have multiplied. In order to get sales stability and profitability, E&C need to differentiate on client care. Many middle-market contracts have a clause of tacit renewal, which means that they are automatically renewed unless the Client expressly asks Engie to terminate it. To terminate a tacit contract, the Client needs to send Engie a termination letter within 2 months before the contract due date. Engie’s mission is to minimize as far as possible the number of these churners ( = clients which terminate their contract). In order to identify “at-risk” clients, they need to build a model for churn prediction, 2 or 3 months before the contract due date. This is your mission if you accept it! Thanks to this solution, the teams may launch specific marketing actions on the identified “at-risk” clients, and then reduce the churn rate on B2B contracts when they get to the due date.

engie_datascience_france_b2b_churn

ENGIE Data Science challenge: Looking at identifying customer churn in the French B2B business.

enterprise-withdrawal-risk-bdci2017

6th solution for Enterprise withdrawal risk BDCI2017

fengyunbei

第二届风云杯机器学习建模大赛---中诚信 第四名解决方案

fengyunbei-1

2017风云杯比赛

flaresolverr

Proxy server to bypass Cloudflare protection

ijcai17_tianchi_rank4

industry-machine-learning

A curated list of applied machine learning and data science notebooks and libraries across different industries.

jd

2017 Global Data Challenge Hosted by JD Finance / JDD—2017京东金融全球数据探索者大赛 金融信贷需求预测

jdata_code

用户对品类下店铺的购买预测

jdd_2017_cup

店铺销量预测