Data processing apparatus, data processing method and semiconductor manufacturing apparatus

A semiconductor manufacturing apparatus in which a processing result is predicted by a prediction model obtained using a feature amount, the semiconductor manufacturing apparatus comprising:

• a control device configured to execute
• a first step of rearranging ranked N first feature amounts in an order from first to N-th, provided that N is a natural number,
• a second step of creating N first data groups, a third step of obtaining a first evaluation index value for evaluating prediction performance of each of the first data groups,
• a fourth step of deleting a part of the first feature amounts based on the first evaluation index values,
• a fifth step of updating an order of second feature amounts, which are feature amounts other than the feature amounts deleted from the first feature amounts, using the first evaluation index values,
• a sixth step of creating second data groups whose number is the same as the number of the second feature amounts,
• a seventh step of obtaining a second evaluation index value for evaluating prediction performance of each of the second data groups, and
• an eighth step of obtaining a prediction model using the second feature amounts when a minimum value of the first evaluation index values is the same as a minimum value of the second evaluation index values, or deleting a part of the second feature amounts based on the second evaluation index values, and updating an order of third feature amounts, which are feature amounts other than the feature amounts deleted from the second feature amounts, using the second evaluation index values when the minimum value of the first evaluation index values is different from the minimum value of the second evaluation index values, wherein
• an N-th first data group has the first to N-th feature amounts of the first feature amounts, and
• an M-th second data group has the first to M-th feature amounts of the second feature amounts, provided that M is the number of the second feature amounts.

A data processing method that obtains a prediction model using a feature amount, the data processing method comprising:

• a first step of rearranging ranked N first feature amounts in an order from first to N-th, provided that N is a natural number;
• a second step of creating N first data groups;
• a third step of obtaining a first evaluation index value for evaluating prediction performance of each of the first data groups;
• a fourth step of deleting a part of the first feature amounts based on the first evaluation index values;
• a fifth step of updating an order of second feature amounts, which are feature amounts other than the feature amounts deleted from the first feature amounts, using the first evaluation index values;
• a sixth step of creating second data groups whose number is the same as the number of the second feature amounts;
• a seventh step of obtaining a second evaluation index value for evaluating prediction performance of each of the second data groups;
• and
• an eighth step of obtaining a prediction model using the second feature amounts when a minimum value of the first evaluation index values is the same as a minimum value of the second evaluation index values, or deleting a part of the second feature amounts based on the second evaluation index values, and updating an order of third feature amounts, which are feature amounts other than the feature amounts deleted from the second feature amounts, using the second evaluation index values when the minimum value of the first evaluation index values is different from the minimum value of the second evaluation index values, wherein
• an N-th first data group has the first to N-th feature amounts of the first feature amounts, and
• an M-th second data group has the first to M-th feature amounts of the second feature amounts, provided that M is the number of the second feature amounts.