$Purpose$– The development of e-grocery allows people to purchase food online and benefit from home delivery service. Nevertheless, a high rate of failed deliveries due to the customer’s absence causes significant loss of logistics efficiency, especially for perishable food. This paper proposes an innovative approach to use customer-related data to optimize e-grocery home delivery. The approach estimates the absence probability of a customer by mining electricity consumption data, in order to improve the success rate of delivery and optimize transportation.

$Design/methodology/approach$ – The methodological approach consists of two stages: a data mining stage that estimates absence probabilities, and an optimization stage to optimize transportation.

$Findings$– Computational experiments reveal that the proposed approach could reduce the total travel distance by 3% to 20%, and theoretically increase the success rate of first-round delivery approximately by18%-26%.

$Research\; limitations/implications$ – The proposed approach combines two attractive research streams on data mining and transportation planning to provide a solution for e-commerce logistics.

$Practical\; implications$ – This study gives an insight to e-grocery retailers and carriers on how to use customer-related data to improve home delivery effectiveness and efficiency.

$Social\; implications$ – The proposed approach can be used to reduce environmental footprint generated by freight distribution in a city, and to improve customers’ experience on online shopping.

$Originality/value$ – Being an experimental study, this work demonstrates the effectiveness of data-driven innovative solutions to e-grocery home delivery problem. The paper provides also a methodological approach to this line of research.