Machine learning in the textile industry
La Paz. 2021 The project began with this question: Will it be possible to improve decision making in the textile industry with Machine Learning? After deciding that we wanted to answer the question, we decided on the industry and…
A learning project shared by the community. The article documents its team, methods and results; it does not establish that the prototype is ready for real-world use.
This archive includes automatic translations. Audio, video and text inside images remain in their original language.
La Paz. 2021
The project began with this question: Will it be possible to improve decision making in the textile industry with Machine Learning? After deciding that we wanted to answer the unknown, we decided on the industry and as we know in Bolivia and we found the textile industry that until 2015, the contribution of the Bolivian textile industry to the Gross Domestic Product (GDP) was 0.9%, equivalent to 451 million dollars, however this sector is severely affected by several problems such as:
- Illegal merchandise entering the country
- Used clothes
- Chinese garments
Because we saw these problems and believe that Bolivia can improve its competitiveness, we chose the textile industry sector to apply Machine Learning.
DEVELOPMENT
We found the dataset on Kaggle, it had the following variables (they are translated into Spanish next to it):
date – Date()
smv – average value per job
day – Day (Mon-Sun)
wip – queued jobs
quarter – 5 periods / month
over time
department – department
incentive – incentive
teamno – Team #
idle time – idle times
no of workers – # of workers
idleman – # of idle workers
no of style change – # of changes
current productivity – current productivity
targeted_productivity – expected productivity
Our dataset obtained from Kaggle had these characteristics, after seeing the variables we saw that the variable SMV value (working average) had some gaps, so seeing its distribution we decided to fill it with the trend of the average and thus we obtained all the data ready to work.
We started with the idea of regression but the methods seemed not to work or gave us very low results so we had to change our approach, then we proceeded to a classification problem, we carried out a normalization of the data and with the data worked on we began to work, here is an example of the correlation matrix that we managed to obtain once we moved on to the data classification part with already normalized data.
Afterwards, models began to be tested, the one with the best predictive results was ADAboost (we insert reference image)
We achieved an accuracy of 0.82 which was simply incredible. After seeing how other methods did not even reach 0.50, we decided to try several additional models such as Random Forest, but the precision was lower (not by much).
In the end we stayed with Adaboost and did an excellent job.
CONCLUSIONS
- With the regression models according to the performance (scores of 0.5) calculated, they do not fit the proposed dataset, a treatment was carried out on the target to become a classification problem.
- The classification models applied to the dataset gave favorable results, especially Adaboost with a score of 0.82.
- The machine learning mechanisms and processes allowed the problem to reuse the model as one of the classification.
Saturdays.AIFollow
WRITTEN BY
Jhonpoolcastro Jcs
More artificial intelligence!
The mission of Saturdays.ai is to make artificial intelligence more accessible (#ai4all) through intensive courses and programs where projects for good are carried out (#ai4good).
Explore our AI master’s programme at https://saturdays.ai/master-ia-online/
If you want to learn more about artificial intelligence join our community at community.saturdays.ai or visit us on our website www.saturdays.ai Join us! Saturdays.AI
A history of the Saturdays.AI community. Originally published on Jan 2, 2022.
← More community stories
