Increasing adoption rates at animal shelters: a two-phase approach to predict length of stay and optimal shelter allocation

Abstract

Background Among the 6–8 million animals that enter the rescue shelters every year, nearly 3–4 million (i.e., 50% of the incoming animals) are euthanized, and 10–25% of them are put to death specifically because of shelter overcrowding each year. The overall goal of this study is to increase the adoption rates at animal shelters. This involves predicting the length of stay of each animal at shelters considering key features such as animal type (dog, cat, etc.), age, gender, breed, animal size, and shelter location. Results Logistic regression, artificial neural network, gradient boosting, and the random forest algorithms were used to develop models to predict the length of stay. The performance of these models was determined using three performance metrics: precision, recall, and F1 score. The results demonstrated that the gradient boosting algorithm performed the best overall, with the highest precision, recall, and F1 score. Upon further observation of the results, it was found that age for dogs (puppy, super senior), multicolor, and large and small size were important predictor variables. Conclusion The findings from this study can be utilized to predict and minimize the animal length of stay in a shelter and euthanization. Future studies involve determining which shelter location will most likely lead to the adoption of that animal. The proposed two-phased tool can be used by rescue shelters to achieve the best compromise solution by making a tradeoff between the adoption speed and relocation cost.

Direct and Indirect Factors Influencing Cat Outcomes at an Animal Shelter

“…Secondly, the interconnectedness of the global model demonstrates how efforts to enact change in one part of the system can result in changes elsewhere, emphasizing that there are many ways to change outcome probabilities. Unlike most other studies predicting shelter outcomes which have relied on predictors specific to the animals or the shelter ( 34 ), our approach incorporates factors outside the shelter and animal which may be important. While this older approach is logical, the results can only inform modifications to practices within the shelter ( 35 ).…”

Results of Behavioral Evaluations Predict Length of Stay for Shelter Dogs

“…Our study focused on a single shelter rather than multiple shelters in different regions, which may reduce the generalizability of our results to other shelters [ 20 , 33 ]. Other limitations of our study derive largely from the necessary safety measures taken by shelter staff conducting the behavioral evaluations.…”

“…Behavior around food, however, represents only one of the many situations and behavioral tendencies typically examined in a shelter evaluation (e.g., fearfulness, sociability, arousal during play, and responses to an unfamiliar person, unfamiliar dog, and handling). The scarcity of information concerning the relationship between behaviors displayed during shelter evaluations and length of stay is surprising given that other factors potentially influencing length of stay have been extensively studied, including canine demographic and phenotypic characteristics [ 17 , 18 , 19 , 20 , 21 , 22 , 23 ], as well as in-kennel behavior [ 17 , 21 , 24 , 25 ] and whether a dog is housed at the shelter or in a foster home [ 26 ].…”

Abandonment of dogs in Latin America: Strategies and ideas

“…Another important aspect of the problem is that the dogs that are not adopted from shelters are euthanized. Researchers estimated that of 6-8 million dogs abandoned in shelters annually, half are euthanized (3-4 million) [71,86]. The environment of shelters is often an extremely stressful factor for dogs due to the excessive noise (the barking of other dogs), the need to modify habits, being locked up, and changes in light/dark cycles.…”