## Evaluation Metric
The evaluation metric for this competition is [RMSE](https://en.wikipedia.org/wiki/Root-mean-square_deviation). The RMSE is commonly used to measure the differences between values. The RMSE for this task is calculated for both E and N errors.


## Benchmark
The benchmark result is from the conventional least-squares method. Because the ground truth of the testing set will not be provided, the E and N error is calculated based on the location near our data collection position. The location is  [22.322101, 114.208885, 0]. 

## Submission Format

**For every GPS Time and Every Satellite in the dataset**, submission files should contain two columns: `ID`, `East_error_base`, and  `North_error_base`. `ID` follows the same sequence with the testing dataset, and within each GPS Time, the satellite sequence should also be the same as that in the testing set. Every `East_error_base` and  `North_error_base` are float values, which mean the E and N based on the above location and your position produced by your model. 


The file should contain a header and have the following format:
```
ID,East_error_base,North_error_base
0,101,-10
1,25
2,0,-67
3,367,87
4,45,145
5,120,123
6,-261,68
7,72,98
8,49,81
9,192,105
10,238,-204
11,-85,-20
12,164,87
13,175.-107
```