Facilitating explanations about analysis of time series data is realized. A time series data analysis apparatus: generates first internal data, based on a first feature data groups, a first internal parameter, and a first learning parameter; transforms a position of first feature data in a feature space, based on the first internal data and a second learning parameter; reallocates the first feature data, based on a first transform result and the first feature data groups; calculates a first predicted value, based on a reallocation result and a third learning parameter; optimizes the first to third learning parameters by statistical gradient, based on a response variable and a first predicted value; generates second internal data, based on second feature data groups, a second internal parameter, and an optimized first learning parameter; transforms a position of the second feature data in a feature space, based on the second internal data and an optimized second learning parameter; and calculates importance data for the second feature data, based on a second transform result and an optimized third learning parameter.
展开▼