Datathon Kaufland Solution – Kaufland case – Team3

Posted 1 CommentPosted in Datathons Solutions

In [1]: import s3fs import pandas as pd import matplotlib.pyplot as plt import matplotlib.dates as mdates import seaborn as sns import numpy as np import pywt In [2]: fs = s3fs.S3FileSystem(anon=True) fs.ls(‘datacases/datathon-2018-2/’) Out[2]: [‘datacases/datathon-2018-2/kaufland’, ‘datacases/datathon-2018-2/nsi’, ‘datacases/datathon-2018-2/ontotext’, ‘datacases/datathon-2018-2/telelink’, ‘datacases/datathon-2018-2/telenor’] In [3]: fs.ls(‘datacases/datathon-2018-2/kaufland’) Out[3]: [‘datacases/datathon-2018-2/kaufland/20180820_Kaufland_case_IoT_and_predictive_maintenance_events.xlsx’, ‘datacases/datathon-2018-2/kaufland/20180920_Kaufland_case_IoT_and_predictive_maintenance.csv’, ‘datacases/datathon-2018-2/kaufland/sample_Kaufland_case_IoT_and_predictive_maintenance.csv’] Events¶ In [4]: with fs.open(‘datacases/datathon-2018-2/kaufland/20180820_Kaufland_case_IoT_and_predictive_maintenance_events.xlsx’, ‘rb’) as f: df_events = pd.read_excel(f) In [5]: df_events Out[5]: […]

Datathon Kaufland Solution – Team Total Kaputt! – Why da faQ the machine broke down?

Posted 1 CommentPosted in Prediction systems

What we tried to do to solve the Kaufland case for the Global Datathon 2018. This article just contains our exploratory data analysis in the form of many plots and some explanations. There isn’t any modeling stage described here.

Datathon Kaufland Solution – LSTM and EDM Models for Predictive Maintenance

Posted 1 CommentPosted in Datathons Solutions

In this paper we propose the use of a combination of LSTM and EDM models to address the issue of anomaly classification and prediction in time series data. Working with sensor data for automated storage and retrieval systems for a German hypermarket chain, we show that predictors based on variance and median methods show sufficient promise in the handling of anomalies.