Bravent wins the 2nd Semifinal of the VI IndesIA Datathon with a solution that predicts production times in the automotive industry!
Bravent has been declared the winner of this second semifinal of the VI IndesIA Datathon, organized by Mecánicas Aparicio.
The challenge for this company was to solve a real problem related to planning and efficiency in industrial environments in the automotive mechanics sector.
With the aim of predicting and reducing production times for these parts, our team presented a proposal that combines advanced predictive models with an analytical chatbot to transform decision-making on the factory floor, with a measurable ROI. Bravent wins the second semifinal of the VI IndesIA Datathon with a solution that predicts production times in the automotive industry!
The challenge: unpredictable production times
In many factories, production orders appear repetitive, but in reality they vary greatly. This lack of predictability causes multiple problems:
- Poor planning and resource allocation
- Missed deadlines and loss of customer satisfaction
- Pressure on staff and increased errors
- Direct impact on product quality
Our solution: prediction + conversation with data
Predictive model with XGBoost
- We started with an exploratory data analysis (EDA) of production order histories, identifying patterns and key variables. After evaluating eight different models (final regression, random forest), we selected the XGBoost predictive model as the most suitable for the solution due to its robustness and accuracy in tabular data, and its high capacity to detect complex interactions.
- Training: the dataset was divided into 70% for training and 30% for validation. A cross-validation strategy was applied to optimize the model’s hyperparameters, minimizing generalization error and ensuring stability in the results.
- Results: prediction of estimated production time with metrics such as MAE and RMSE, obtaining an 80% improvement in manual cutting predictions and a 66% improvement in the manual folding model.
- Application: allows delays to be anticipated and orders to be prioritized according to risk. The challenge: unpredictable production times
Intuitive interface and agile workflow
- The user uploads an Excel file with the orders.
- The system performs the analysis and generates predictions instantly.
- The chatbot answers questions about the data and suggests actions.
Impact and value for the company
Our solution provides tangible benefits:
- Reduced costs and downtime
- Improved inventory planning
- Data-driven decisions in seconds
- Increased competitiveness and on-time delivery
- Estimated savings in operating costs and overtime
ROI – 40% reduction in unplanned production hours
Bravent’s project stood out for the high ROI it brings to the company, with a reduction of nearly 40% in unplanned production hours and the resulting savings in personnel costs and production downtime.
Future: towards an intelligent “Super-Agent”
We are working on an evolution of the system that will include:
- Agents that understand natural language and extract key variables.
- Intelligent routers that select the most appropriate model for each case.
- Integration with ERP/MES systems and automatic notifications.
- A 24/7 assistant that centralizes diagnostics, predictions, and recommendations.
This achievement not only demonstrates the talent and commitment of our AI team, BraventIA, but also our commitment to technological solutions that have a real impact on the industry. Thank you to everyone who made this possible!
This solution is scalable and applicable to other industries with similar problems. Would you like to know how it can be applied to your company? Contact us and we will tell you all about it.
For more details, you can contact us at Info@bravent.net
