Table 2 Variable definitions
From: Predicting abnormal trading behavior from internet rumor propagation: a machine learning approach
Attribute name | Notation | Description | Source/Calculation | |
|---|---|---|---|---|
Post | ||||
Accumulation | In the preceding 90 days | PA_90 | The summed daily post of a stock in CMoney up to the preceding X days. (X = 30, 60, 90) | CMoney |
In the preceding 60 days | PA_60 | |||
in the preceding 30 days | PA_30 | |||
Variation | The preceding 60th and 90th day | PV_90 | Between the preceding X1th and X2th day, the difference in the volume of posts within a day based on a stock in CMoney. ([X1, X2] = [0,30], [30,60], [60,90]) | CMoney |
the preceding 30th and 60th day | PV_60 | |||
the preceding 30th day | PV_30 | |||
Reply | ||||
Accumulation | In the preceding 90 days | RA_90 | The summed daily reply of all post for a stock in CMoney up to the preceding X days. (X = 30, 60, 90) | CMoney |
In the preceding 60 days | RA_60 | |||
In the preceding 30 days | RA_30 | |||
Variation | The preceding 60th and 90th day | RV_90 | Between the preceding X1th and X2th day, the difference in the volume of replies within a day based on all posts of a stock in CMoney. ([X1, X2] = [0,30], [30,60], [60,90]) | CMoney |
The preceding 30th and 60th day | RV_60 | |||
The preceding 30th day | RV_30 | |||
Like | ||||
Accumulation | In the preceding 90 days | LA_90 | The summed daily like of all post for a stock in CMoney up to the preceding X days. (X = 30, 60, 90) | CMoney |
In the preceding 60 days | LA_60 | |||
In the preceding 30 days | LA_30 | |||
Variation | The preceding 60th and 90th day | LV_90 | Between the preceding X1th and X2th day, the difference in the volume of likes within a day based on all posts of a stock in CMoney. ([X1, X2] = [0,30], [30,60], [60,90]) | CMoney |
The preceding 30th and 60th day | LV_60 | |||
The preceding 30th day | LV_30 | |||
Industry | ||||
Biotechnology and medicine | BM | There are 6 industries including Biotechnology and Medicine, Cultural and Creative Industry, Electronics Manufacturing, Information and Communications Technology, Other Manufacturing and Other Service Industry | TEJ | |
Cultural and creative industry | CC | |||
Electronics manufacturing | EM | |||
Information and communications technology | IC | |||
Other manufacturing | OM | |||
Other service industry | OS | |||
Management shocks | FC | The variable was flagged (“1” = “Yes”, and “0” = “No”) whether the stocks have ever had management shocks such as strikes in the preceding year | ||
Incorporation type | I_type | There are 2 types including General stock, and KY stock which is a stock registered abroad with initial public offering in Taiwan | ||
Shareholdings variation of major stockholders with above 600 lots | ||||
The preceding 30th day | S600_30 | The shareholdings of preceding Xth day for Major stockholders with above 600 lots. The major-stockholders definition is based on the multiple partitioning method. (X = 30, 60, 90) | ||
The preceding 60th day | S600_60 | |||
The preceding 90th day | S600_90 | |||
Shareholdings variation of individual stockholders with 20 lots and below | ||||
The preceding 30th day | S20_30 | The shareholdings of the preceding Xth day for individual stockholders with 20 lots and below. The individual-stockholders definition is based on the multiple partitioning method. (X = 30, 60, 90) | ||
The preceding 60th day | S20_60 | |||
The preceding 90th day | S20_90 | |||