Humans make decisions based on their internal value function, and its shape is known to be distorted and biased around a point, which the research community of behavior economics refers to as the reference point. People intensify activities that come to lie within the reach of their reference point, and abstain from acts that would incur losses once they've crossed the point. However, the impact of past experiences on decision making around the reference point has not been well studied. By analyzing a long series of user-level decisions gathered from a competitive programming website, we find that history has a clear impact on user's decision making around the reference point. Past experiences can strengthen, and sometimes weaken, the decision bias around the reference point. Experiences of past difficulties can strengthen the tendency towards loss aversion after achieving the reference point. When a person crosses a reference point for the first time, the cognitive decision bias is significant. However, repeating this crossing gradually weakens the effect. We also show the value of our insights in the task of predicting user behavior. Prediction models incorporating our insights may be used for motivating people to remain more active.

Data often accumulates in tabular format with many attribute items, and prediction using machine learning adds value to data for business. However, studies on machine learning for tabular data only input attribute values, which reduces accuracy. Therefore, we propose an inference method that inputs attribute values and values from aggregated tabular data that has varying attribute values for each attribute item. In an experiment, we compared our proposed method with AutoGluon-Tabular using AutoML benchmark datasets. Our proposed method achieved the highest accuracy for 21 out of 39 datasets.

Sequences of events including infectious disease outbreaks, social network activities, and crimes are ubiquitous and the data on such events carry essential information about the underlying diffusion processes between communities (e.g., regions, online user groups). Modeling diffusion processes and predicting future events are crucial in many applications including epidemic control, viral marketing, and predictive policing. Hawkes processes offer a central tool for modeling the diffusion processes, in which the influence from the past events is described by the triggering kernel. However, the triggering kernel parameters, which govern how each community is influenced by the past events, are assumed to be static over time. In the real world, the diffusion processes depend not only on the influences from the past, but also the current (time-evolving) states of the communities, e.g., people's awareness of the disease and people's current interests. In this paper, we propose a novel Hawkes process model that is able to capture the underlying dynamics of community states behind the diffusion processes and predict the occurrences of events based on the dynamics. Specifically, we model the latent dynamic function that encodes these hidden dynamics by a mixture of neural networks. Then we design the triggering kernel using the latent dynamic function and its integral. The proposed method, termed DHP (Dynamic Hawkes Processes), offers a flexible way to learn complex representations of the time-evolving communities' states, while at the same time it allows to computing the exact likelihood, which makes parameter learning tractable. Extensive experiments on four real-world event datasets show that DHP outperforms five widely adopted methods for event prediction.

Predicting when and where events will occur in cities, like taxi pick-ups, crimes, and vehicle collisions, is a challenging and important problem with many applications in fields such as urban planning, transportation optimization and location-based marketing. Though many point processes have been proposed to model events in a continuous spatio-temporal space, none of them allow for the consideration of the rich contextual factors that affect event occurrence, such as weather, social activities, geographical characteristics, and traffic. In this paper, we propose DMPP (Deep Mixture Point Processes), a point process model for predicting spatio-temporal events with the use of rich contextual information; a key advance is its incorporation of the heterogeneous and high-dimensional context available in image and text data. Specifically, we design the intensity of our point process model as a mixture of kernels, where the mixture weights are modeled by a deep neural network. This formulation allows us to automatically learn the complex nonlinear effects of the contextual factors on event occurrence. At the same time, this formulation makes analytical integration over the intensity, which is required for point process estimation, tractable. We use real-world data sets from different domains to demonstrate that DMPP has better predictive performance than existing methods.

Predicting traffic flows on multiple inter-city roads play a critical role in traffic management. Temporal patterns of traffic flow can dynamically change over time as a result of traffic management measures such as the construction of new roads. Given this possibility, it is sensible to use only recent data, instead of all past data. In this study, by incorporating the latent factor model into a conventional approach, we construct a novel traffic prediction method for multiple inter-city roads based on the most recent training data. This formulation leads to a reduction in the number of model parameters, since it assumes that there is a set of patterns underlying the data (in our case, the periodic patterns shared across roads in traffic flow data), which inherently offers robustness against sparse observations. In addition, we adopt stochastic variational Bayes method to solve the optimization problem, which allows us to update model parameters online. By continually updating the model based on the most recent training data, we can instantly provide accurate predictions of inter-city traffic flow that have intermittently changing patterns. Using a real-world traffic flow dataset collected in the Greater Tokyo Area via GPS-equipped mobile phones, we evaluate the predictive performance of the proposed method, and confirm that it performs better than existing methods in the sparse domain.

Determining routes that provide opportunities to satisfy the various demands of users is still an open problem. This is because it is virtually impossible to manually quantify the characteristics of each road and there are few resources describing roads directly such that we meet any demand that may arise. The goal of this study is to automatically quantify the characteristics of roads for demands that can be described using keywords such as “fashionable”. To achieve this goal, we propose a two-stage method that analyzes social media and road networks. First, our method estimates the topic distribution (i.e., the characteristics) of each point-of-interest (POI) by analyzing geotagged texts with the Latent Dirichlet Allocation model. Next, it uses a Markov random field model to estimate the characteristics of each road on the basis of those of POIs and the road networks associated with the POIs. Experiments on real datasets demonstrate that our method achieves statistically significant improvements over baseline methods in terms of ranking quality in the information retrieval for roads in three areas given 25 keywords.

This paper focuses on task assignments to workers in mobile crowdsoucing systems. The current method does not work so well since it considers only workers who are ready to work at the time of optimization. Our method handles workers' day-long schedules, creates a `time-extended' worker-task graph that expresses the relationships between workers and tasks over a time period and finds the best set of worker-task-time triples. Our evaluation using real world visiting logs shows it increases the rate of assigned tasks by more than 8.2% compared with a state-of-the-art assignment method.

We propose a new method for estimating user attributes (gender, age, occupation, and interests) of a Twitter user from the user's contents (profile document and tweets) and social neighbors, i.e. those whom the user has mentioned. Our labeling method is able to collect a large amount of training data automatically by using Twitter users associated with a blog account. Furthermore, we experiment estimation methods using social neighbors with three adjustable levels of its information and show that our method, which uses the target user's profile document and tweets and the neighbors' profile documents (not including tweets), achieves the best accuracy.

Information needs expressed by using the same query for a search engine might be totally different, whether on week days or weekends, or during the day or at night. For queries having no temporal changes in search intentions, the same search results ranking may be returned regardless of the time, but for those with temporal changes the ranking must be suitably altered depending on the time of input. To achieve time-dependent search results rankings, we focus on the temporal changes in the search intentions. We present the results obtained by analyzing a commercial search engine log and propose a method of detecting queries showing periodic changes in the search intentions.

This paper proposes a highly effective geographic information retrieval method. It assesses the extent implied by place names in documents and then emphasizes place names that are highly specific in terms of identifying locations. Furthermore, the method also assesses the proximity between place names and keywords in each document and adjusts the document score based on the proximity between place name associated with user's geographic intention and keywords associated with user's query. Evaluation results show that the two methods proposed herein offer improved performance according to some TREC-style evaluation metrics.

This paper proposes a novel Geo-IR ranking method that realizes effective searches that emphasize the user's immediate surroundings. It assesses the extent implied by place names in documents and then emphasizes place names that are highly specific in terms of identifying locations.