diff --git a/PaddleST/README.md b/PaddleST/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1a23eb54e0d6baf085949a8985263173983e5623
--- /dev/null
+++ b/PaddleST/README.md
@@ -0,0 +1,5 @@
+## PaddleST
+
+- Paddle models for Spatial and Temporal
+
+- Include Research and Industry application
diff --git a/PaddleST/Research/CIKM2019-MONOPOLY/README.md b/PaddleST/Research/CIKM2019-MONOPOLY/README.md
index 99b1b626f4a425f1691951148c9008e6f4bdf960..6355229e2c16f0bc2047836805462f76767ea117 100644
--- a/PaddleST/Research/CIKM2019-MONOPOLY/README.md
+++ b/PaddleST/Research/CIKM2019-MONOPOLY/README.md
@@ -1,16 +1,17 @@
 # MONOPOLY
 
-## 简介
+## 任务说明(Introduction)
 
-### 任务说明
+互联网地图，作为一个经典的时空大数据平台，承载了大量有关固定资产（Point-of-Interest，简称POI)、出行轨迹、用户画像、地点查询等相关信息。
 
-互联网地图，作为一个经典的时空大数据平台，收集了大量有关固定资产（Point-of-Interest，简称POI)、出行轨迹、地点查询等相关信息。
+![](docs/real_estates.png)
 
-Monopoly是一个POI商业智能算法，能够利用少量的房产价格，对大量其他的固定资产进行价值估计。
+Monopoly是一个实用的POI商业智能算法，能够利用少量的房产价格，对大量其他的固定资产进行价值估计。
+该算法全面适配MapReduce的分布式计算框架，能够快速用于工业部署。
 
-文章地址：XXXX
+![](docs/framework.png)
 
-### 研究意义与发现
+这个有趣的想法最初来源于经典的棋盘类游戏“大富翁”，因此我们也以同样的英文名来命名这个算法。
 
 1）Monopoly能够帮助我们发现：各个城市居民对于不同类型公共资产价格评估的偏好，并且给出量化分析。
 
@@ -18,10 +19,13 @@ Monopoly是一个POI商业智能算法，能够利用少量的房产价格，对
 
 3）Monopoly能够帮助我们确定：评估一个固定资产价格需要考虑的空间范围。
 
-### 效果说明
+The value assessment of private properties is an attractive but challenging task which is widely concerned by a majority of people around the world. A prolonged topic among us is how much is my house worth?. To answer this question, most experienced agencies would like to price a property given the factors of its attributes as well as the demographics and the public facilities around it. However, no one knows the exact prices of these factors, especially the values of public facilities which may help assess private properties.  
+We introduce our newly launched project Monopoly (named after a classic board game) in which we propose a distributed approach for revaluing private properties by learning to price public facilities (such as hospitals, schools, and metros) with the large-scale urban data we have accumulated via Baidu Maps. To be specific, our method organizes many points of interest (POIs) into an undirected weighted graph and formulates multiple factors including the virtual prices of surrounding public facilities as adaptive variables to parallelly estimate the housing prices we know. Then the prices of both public facilities and private properties can be iteratively updated according to the loss of prediction until convergence. 
+We have conducted extensive experiments with the large-scale urban data of several metropolises in China. Results show that our approach outperforms several mainstream methods with significant margins. Further insights from more in-depth discussions demonstrate that the ''Monopoly'' is an innovative application in the interdisciplinary field of business intelligence and urban computing, and it will be beneficial to tens of millions of our users for investments and to the governments for urban planning as well as taxation. 
 
+## 安装说明(Install Guide)
 
-## 安装说明
+### 环境准备
 
 1. paddle安装
 
@@ -44,7 +48,8 @@ Monopoly是一个POI商业智能算法，能够利用少量的房产价格，对
     python版本依赖python 2.7
 
 
-### 开始第一次模型调用
+### 实验说明
+
 1. 数据准备
 
     TODO
@@ -60,11 +65,23 @@ Monopoly是一个POI商业智能算法，能够利用少量的房产价格，对
 
 3. 模型评估
     ```
-    sh run.sh -c conf/house_price/house_price.local.conf -m pred
+    c=bj
+    sh run.sh -c conf/house_price/house_price.local.conf -m pred > $c.out
     cat $c.out | grep ^qid | python utils/calc_metric.py
     ```
 
-## Reference this paper
-=====
+## 论文下载(Paper Download)
+
+Please feel free to review our paper :)
+
+[Full Text](TODO)
+
+[ACM DL](TODO)
+
+
+## 引用格式(Paper Citation)
+
+[Miao Fan](https://sites.google.com/view/miao-fan/home), [Jizhou Huang](http://ir.hit.edu.cn/~huangjizhou/), An Zhuo, Ying Li, Ping Li, Haifeng Wang. MONOPOLY: Learning to Price Public Facilities for Revaluing Private Properties with Large-scale Urban Data, The 28th International Conference on Information and Knowledge Management (CIKM'19), pp. XXX-XXX. [bib](xxx)
+
 
 
diff --git a/PaddleST/Research/CIKM2019-MONOPOLY/docs/framework.png b/PaddleST/Research/CIKM2019-MONOPOLY/docs/framework.png
new file mode 100644
index 0000000000000000000000000000000000000000..791beda137bf96ad3f7de1e3b0c79fc799fb1ba7
Binary files /dev/null and b/PaddleST/Research/CIKM2019-MONOPOLY/docs/framework.png differ
diff --git a/PaddleST/Research/CIKM2019-MONOPOLY/docs/real_estates.png b/PaddleST/Research/CIKM2019-MONOPOLY/docs/real_estates.png
new file mode 100644
index 0000000000000000000000000000000000000000..63f8e4b19ef4a5b87ea62edf22b33f07905d319a
Binary files /dev/null and b/PaddleST/Research/CIKM2019-MONOPOLY/docs/real_estates.png differ
diff --git a/PaddleST/Research/README.md b/PaddleST/Research/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cf0ee914d0e0dfc04b9da43a237618932319f011
--- /dev/null
+++ b/PaddleST/Research/README.md
@@ -0,0 +1,5 @@
+## PaddleST for Research
+
+- Provide the codes and the datasets of the latest research on Spatial and Temporal analysis.
+
+- Enable the developers and researchers to easily reproduce the experiments of the published academic papers and quickly develop their new methods.