Browsing by Author "Borges, Lucas D."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- Data mining in retail sectorPublication . Borges, Lucas D.; Pereira, Ana I.; Vaz, Clara B.; Lanes, Matusalém M.The retailsectorisoneofPortugal’smostrelevanteconomicactivitiesbecausein2021it was the sector that employed the most Portuguese people and the second largest contributor t gross fixed capital formation. Despite this,in the same year it was the third sector with th most accidents at work.There fore, this master’s thesis aims to apply data mining techniques to improve work accidents prevention using internal and external data from a Portuguese retail company. The company provide dinternal data on stores, accidents and employees, which was the nintegrated with weather information collected via anexternal API. Th correlation analysis was applied separating the data by store and by district and idemonstrated a weak correlation between the features studied and the occurrence of accidents at work. Further more, ML models were trained using the same features with the intention of classifying the data between occurrence(1) ornon-occurrence(0) ofaccidents, also separating by store and by district while comparing 8ML algorithms. Another categorization of stores was testedusing a clustering algorithm along with a number of clusters optimizing method.The stores were then dividedin to clusters so that the same correlation analysis and ML classification models could be implemented for comparison. The correlation analysis per-cluster yielded no different results from the previous ones. On the other hand, the classificationa lgorithms trained by cluster performed better,with the Multilayer Perceptron algorithm obtaining Recall = 0.7959.
- Effect of Weather Conditions and Transactions Records on Work Accidents in the Retail Sector – A Case StudyPublication . Borges, Lucas D.; Sena, Inês; Marcelino, Vitor Fernandes; Silva, Felipe G.; Fernandes, Florbela P.; Pacheco, Maria F.; Vaz, Clara B.; Lima, José; Pereira, Ana I.Weather change plays an important role in work-related accidents, it impairs people’s cognitive abilities, increasing the risk of injuries and accidents. Furthermore, weather conditions can cause an increase or decrease in daily sales in the retail sector by influencing individual behaviors. The increase in transactions, in turn, leads employees to fatigue and overload, which can also increase the risk of injuries and accidents. This work aims to conduct a case study in a company in the retail sector to verify whether the transactions records in stores and the weather conditions of each district in mainland Portugal impact the occurrence of work accidents, as well as to perform predictive analysis of the occurrence or non-occurrence of work accidents in each district using these data and comparing different machine learning techniques. The correlation analysis of the occurrence or non-occurrence of work accidents with weather conditions and some transactions pointed out the nonexistence of correlation between the data. Evaluating the precision and the confusion matrix of the predictive models, the study indicates a predisposition of the models to predict the non-occurrence of work accidents to the detriment of the ability to predict the occurrence of work accidents.