Ecological interactions and the Netflix problem
Open Access
Abstract
Species interactions are a key component of ecosystems but we generally have an incomplete picture of who-eats-who in a given community. Different techniques have been devised to predict species interactions using theoretical models or abundances. Here, we explore the K nearest neighbour approach, with a special emphasis on recommendation, along with a supervised machine learning technique. Recommenders are algorithms developed for companies like Netflix to predict whether a customer will like a product given the preferences of similar customers. These machine learning techniques are well-suited to study binary ecological interactions since they focus on positive-only data. By removing a prey from a predator, we find that recommenders can guess the missing prey around 50% of the times on the first try, with up to 881 possibilities. Traits do not improve significantly the results for the K nearest neighbour, although a simple test with a supervised learning approach (random forests) show we can predict interactions with high accuracy using only three traits per species. This result shows that binary interactions can be predicted without regard to the ecological community given only three variables: body mass and two variables for the species’ phylogeny. These techniques are complementary, as recommenders can predict interactions in the absence of traits, using only information about other species’ interactions, while supervised learning algorithms such as random forests base their predictions on traits only but do not exploit other species’ interactions. Further work should focus on developing custom similarity measures specialized for ecology to improve the KNN algorithms and using richer data to capture indirect relationships between species.Keywords
All Related Versions
Funding Information
- National Sciences and Engineering Research Council of Canada
- Microsoft
- Nvidia
- Canada Research Chair Program
- NSERC Discovery Grant
- FQRNT Nouveau Chercheur grant
This publication has 25 references indexed in Scilit:
- The dimensionality of ecological networksEcology Letters, 2013
- Hierarchical Bayesian models in ecology: Reconstructing species interaction networks from non-homogeneous species abundance dataEcological Informatics, 2012
- Ecophylogenetics: advances and perspectivesBiological Reviews, 2012
- Structural dynamics and robustness of food websEcology Letters, 2010
- Exact Matrix Completion via Convex OptimizationFoundations of Computational Mathematics, 2009
- Improving the analyses of nestedness for large sets of matricesEnvironmental Modelling & Software, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Markov logic networksMachine Learning, 2006
- Simple rules yield complex food websNature, 2000
- An Algorithm for Finding Best Matches in Logarithmic Expected TimeACM Transactions on Mathematical Software, 1977