participants
This topic is about the quality prediction of manufacturing processes. By adopting Machine Learning methods, parameters used during the manufacturing processes will be used to build models for quality prediction. The data is provided by an opto-electronic technology company. By analyzing the data, results of the manufacturing process can be accurately predicted. This can not only improve product quality, but also lower the costs of manufacturing.
The complexity of the manufacturing processes puts challenges on analyzation and optimization. Many factors will influence product quality, such as machine parameters, the amount and ratio of materials (primary materials and accessory materials), temperature, pressure, time, etc., and these factors can impact the result either directly or indirectly. Different products have different requirements, or acceptable quality level. An accurate model can help understand the relative importance of different factors and identify how the parameters can influence the quality, and thus can directly improve manufacturing process analyzation and optimization. In this topic, participants need to predict two target numbers regarding each set of parameters.
The following awards will be given to the participants who have achieved all of the following: the top three participants whose score on the Private Leaderboard is lower than the baseline (MAE < 0.007) and the report is submitted before 7/22.
First place: 150,000 discount points of hicloud + NTD 50,000 (Tax included)
Second place: 100,000 discount points of hicloud + NTD 30,000 (Tax included)
Third place: 50,000 discount points of hicloud + NTD 20,000 (Tax included)
Honorable mention: 50,000 discount points of hicloud (multiple winners, depends on the final result)
* Hicloud discount points were provided by Chunghwa Telecom
Notes:
1. Hicloud points can redeem service charge. After the discount, the price will be charged at 30% off based on the list price automatically.
2. Chunghwa Telecom deserves the right to make changes to the terms and conditions herein.
3. The example of discount points calculation can be referred to https://aidea-web.tw/computing
Report content should include hardware and software specifications, data preprocessing, choice of models, and parameters adjustments, and etc.
The activity time will be based on Taiwan Standard Time (UTC+8), and the schedule is as follows.
Time | Event |
---|---|
2020/06/12 | Registration begins |
2020/06/19 | Submission begins |
2020/07/15 | Submission deadline |
2020/07/22 | Report submission deadline |
2020/07/24 | Awards announcement |
Evaluations are conducted by calculating the Mean Absolute Error(MAE)[1]
The formula is as follows:
$$MAE = {\sum_{i=1}^{n} \left| (y_i - \hat{y}_i) \right| \over n} $$
Reference
[1] Mean Absolute Error (MAE):
https://en.wikipedia.org/wiki/Mean_absolute_error