Financial time series forecasting is a crucial measure for improving and making more robust financial decisions throughout the world. Noisy data and non-stationarity information are the two key factors in financial time series prediction. This paper proposes twin support vector regression for financial time series prediction to deal with noisy data and nonstationary information. Various interesting financial time series datasets across a wide range of industries, such as information technology, the stock market, the banking sector, and the oil and petroleum sector, are used for numerical experiments. Further, to test the accuracy of the prediction of the time series, the root mean squared error and the standard deviation are computed, which clearly indicate the usefulness and applicability of the proposed method. The twin support vector regression is computationally faster than other standard support vector regression on the given 44 datasets.

Capsule Networks (CapsNet) are recently proposed multi-stage computational models specialized for entity representation and discovery in image data. CapsNet employs iterative routing that shapes how the information cascades through different levels of interpretations. In this work, we investigate i) how the routing affects the CapsNet model fitting, ii) how the representation by capsules helps discover global structures in data distribution and iii) how learned data representation adapts and generalizes to new tasks. Our investigation shows: i) routing operation determines the certainty with which one layer of capsules pass information to the layer above, and the appropriate level of certainty is related to the model fitness, ii) in a designed experiment using data with a known 2D structure, capsule representations allow more meaningful 2D manifold embedding than neurons in a standard CNN do and iii) compared to neurons of standard CNN, capsules of successive layers are less coupled and more adaptive to new data distribution.Corresponding author, email: mazy@gpnu.edu.cn 4 To be more specific, the "atomic units" refer to the basic random variables that we are concerned with.In practical image/video analytic tasks, this concept of lower "convolutional" layers correspond to an element of a channel at a particular image location.

Accessibility “to” and “through” public transit has been one key transit planning indicator that reflects service quality. Occasionally, transit agencies may consider a fare change to maintain operations or to attract more passengers. However, transit agencies do not usually consider the effect of such fare change on passengers’ accessibility. This paper investigates that effect. A multinomial logit mode choice model is developed to measure the monetary value of transit users’ travel time. Then, the cumulative opportunity measure of accessibility is used to examine the change in job accessibility after a recent transit fare increase in the city of Kelowna, British Columbia, Canada. The results show that the loss in job accessibility resulting from transit fare increase is inversely proportional to the length of the trip, given a flat fare structure. The findings of this paper should be kept in mind before a transit agency rethinks transit fare structures. For example, a transit agency could consider applying a zone-based fare structure as opposed to a flat fare structure to ensure better equity for all transit users.

No abstract