Using big data to enhance the bosch production line performance: A Kaggle challenge

Abstract

This paper describes our approach to the Bosch production line performance challenge run by Kaggle.com. Maximizing the production yield is at the heart of the manufacturing industry. At the Bosch assembly line, data is recorded for products as they progress through each stage. Data science methods are applied to this huge data repository consisting records of tests and measurements made for each component along the assembly line to predict internal failures. We found that it is possible to train a model that predicts which parts are most likely to fail. Thus a smarter failure detection system can be built and the parts tagged likely to fail can be salvaged to decrease operating costs and increase the profit margins.

Applied machine learning to predict stress hotspots I: Face centered cubic materials

“…Machine learning (ML) techniques are well established and have been applied to different fields such as advanced manufacturing, financial services, health care, marketing and sales, 7 robotics and transportation (LeCun et al (2015); Mangal and Kumar (2016)). Machine learning is a statistical framework that automates analytical model fitting for data analysis such as finding structure in data (clustering) and making data-driven predictions or decisions.…”

Applied machine learning to predict stress hotspots II: Hexagonal close packed materials

“…Thus, we can vary the CRSS ratio and crystallographic texture to analyze their impact on stress hotspot 2 formation. Machine learning (ML) techniques are gaining popularity and have been applied successfully to various fields (LeCun et al (2015); Bose and Mahapatra (2001); Lavecchia (2015); McMahan et al (2013); Mangal and Kumar (2016)) to gain insights and relationships between features or attributes of different kinds. These techniques are finding their way into the materials science domain (Rajan (2015); Fedorov and Shamanaev (2017); Gómez-Bombarelli et al (2016)), in areas such as molecular informatics (Yao et al (2017)), predicting deformation twinning based on the local structure (Orme et al (2016)) and predicting phase diagrams (Meredig et al (2014)).…”

Analysing time pressure in professional tennis

“…For the prediction model, we used the Extreme Gradient Boosting (XGB) algorithm (Chen, He and Benesty, 2015). The algorithm is known for its proven efficiency, speed and flexibility and was therefore used many times at Kaggle tournaments by winning teams (Mangal and Kumar, 2016;Sheridan., 2016). We used 100 trees as a parameter for XGB and left other parameters with default.…”