Aiming at the problem of outlier detection of mixed attributes，this paper proposes a method for outlier detection of mixed attributes based on neighborhood approximate accuracy. First， a heterogeneous neighborhood relationship metric is defined to represent the proximity between mixed data. Then， a specific neighborhood approximation accuracy is defined to construct the neighborhood grain outliers. Further， a neighborhood approximation accuracy-based outlier factor is defined and a neighborhood approximation accuracy-based outlier detection （NAAOD） algorithm is proposed. Finally，the effectiveness of the NAAOD algorithm is evaluated using the UCI dataset. Theoretical research and experimental results show that the NAAOD algorithm is effective for detecting outliers with mixed attributes.