Human-wildlife interactions can have negative consequences when they involve large carnivores. Spatial risk modelling could serve as a useful management approach for predicting and pre-emptively mitigating negative interactions. We present a mechanistic modelling framework and examine interactions between humans and sloth bears (Melursus ursinus) in a multi-use forest landscape of central India. We first assessed patterns and determinants of bear distribution across the landscape using indirect sign surveys. At the same spatial scale, we then estimated spatial probabilities of bear attacks on people using information from 675 interviews with local residents, incorporating estimates of distribution probabilities from the previous step. We found the average occupancy probability across 128 grid-cells to be 0.77 (SE = 0.03). Bear occupancy was influenced by terrain ruggedness, forest composition and configuration, vegetation productivity and size of human settlements. The average probability of a bear attack in any given grid-cell was 0.61 (SE = 0.03), mostly determined by bear occurrence patterns, forest cover, terrain ruggedness, and size of human settlements. Using spatial information on people's dependence on forest resources, we identified locations with the highest risk of bear attacks. Our study demonstrates that human attacks by bears-generally believed to be random or incidental-in fact showed deterministic patterns. Our framework can be applied to other scenarios involving human-wildlife conflicts. Based on our findings, we propose that a proactive co-management approach which involves collaboration between wildlife managers and local residents could help better manage human-bear conflicts in central India and elsewhere across the species' range.