CLIFT: Cross-City Mobility-Derived Lifestyle Pattern Transfer for Improved Multi-City Next Location Prediction

Effective human mobility modeling and prediction constitute the core prerequisites for various location-based applications. To encourage research in this direction, the ACM SIGSPATIAL Cup 2025 posed the challenge of predicting human mobility trajectories from a sparse multi-city dataset. This paper presents our solution, MoBERT, a BERT-like model that adapts and leverages mobility semantics with additional direction and distance prediction, providing supplementary supervision signals for robust feature learning. MoBERT models are trained in stages through curriculum learning, where augmented trajectories are ordered by increasing mobility entropy for training with progressively increasing difficulty. The final score of our method is 0.14609, as measured by average GEO-BLEU distances across four cities. Finally, we analyze the results and discuss insights from our approach.

The prediction of human and vehicle mobility in a city is becoming an attracting field. This topic attracts researchers from broad fields including behavioral sciences, where understanding the complexity of the human mobility behavior is one of the hot topic, and also to the industrial partners, who apply such results to many beneficial applications. Recent progress to sensing human mobility via smartphones is boosting this trend. However, due to the complexity and context-dependence of human behavior and the incompleteness and noise of geospatial data collecting from various sensors, the prediction of human and vehicle mobility is still far from solved. This workshop aimed at collecting contributions on the cutting-edge studies in human mobility description, modeling, intelligent computational method which can advance the human and vehicle prediction research. Potential topics included, but were not limited to 1) The next location prediction of individual mobility, 2) The crowd or population mobility prediction, 3) Dynamics of pedestrians, 4) commute flow and migration flow, 5) Traffic congestion, road usage forecast and optimal vehicle routing, 6) Social event forecast using geospatial data, 7) Novel agent mobility simulators, and 8) Case studies of mobility estimation in academia as well as in industrial field.

This paper describes a human mobility prediction system which build by KDDI Research, Inc. to submit for Human Mobility Prediction Challenge (HuMob Challenge) 2024. The system consists of 6 human mobility prediction subsystems: 5 transformer-based subsystems; LSTM (Long Short-Term Memory) based subsystem. The system selects the best prediction result out of 6 outputs. Since a task of HuMob Challenge 2024 is to predict human mobility of day 61 to 75 using given human mobility data of day 1 to 60, the selection logic is built by the prediction performance of day 45 to 60 data. Although the selection logic is based on the prediction results on closed data set, the selection thought to work precisely.

In recent decades, the frequency and intensity of natural disasters has increased significantly, and this trend is expected to continue. Therefore, understanding and predicting human behavior and mobility during a disaster will play a vital role in planning effective humanitarian relief, disaster management, and long-term societal reconstruction. However, such research is very difficult to perform owing to the uniqueness of various disasters and the unavailability of reliable and large-scale human mobility data. In this study, we collect big and heterogeneous data (e.g., GPS records of 1.6 million users 1 over 3 years, data on earthquakes that have occurred in Japan over 4 years, news report data, and transportation network data) to study human mobility following natural disasters. An empirical analysis is conducted to explore the basic laws governing human mobility following disasters, and an effective human mobility model is developed to predict and simulate population movements. The experimental results demonstrate the efficiency of our model, and they suggest that human mobility following disasters can be significantly more predictable and be more easily simulated than previously thought.

Location prediction has attracted wide attention in human mobility prediction because of the popularity of location-based social networks. Existing location prediction methods have achieved remarkable development in centrally stored datasets. However, these datasets contain privacy data about user behaviors and may cause privacy issues. A location prediction method is proposed in our work to predict human movement behavior using federated learning techniques in which the data are stored in different clients and different clients cooperate to train to extract useful users’ behavior information and prevent the disclosure of privacy information. Firstly, we put forward an innovative spatiotemporal location prediction framework (STLPF) for location prediction by integrating spatiotemporal information in local and global views on each client and propose a new loss function to optimize the model. Secondly, we design a new personalized federated learning framework in which clients can cooperatively train their personalized models in the absence of a global model. Finally, the numerous experimental results on check-in datasets further show that our privacy-protected method is superior and more effective than various baseline approaches.

A probabilistic kernel method for human mobility prediction with smartphones

As an initial research in human mobility, human mobility prediction can be done by using a time-series predictor algorithm, one of which is ARIMA. ARIMA is short of the integrated moving-average autoregressive. The order of the ARIMA model is represented by the ARIMA symbol (p, d, q), where p is the order of the autoregressive part, d is the order of differencing and q is the order of moving-average process. The research regarding the application of human mobility conducted through five phases, including data collection, data pre-processing, data model building, data prediction and data evaluation. We conducted three times of experiments with different parameters. We defined different value for D, Seasonality, MALags, SMALags and Variance. Based on experiment as conclusion of this research obtained that the best parameter values to get the best MAPE Longitude and MAPE Latitude are Constant = 0, D= 1, Seasonality= 12, MALags = 1, SMALags=12 with MAPE Lon: 0.037433% and MAPE Lat: 0.11632%

The quality of life for people in urban regions can be improved by predicting urban human mobility and adjusting urban planning accordingly. In this study, we compared several possible variables to verify whether a gravity model (a human mobility prediction model borrowed from Newtonian mechanics) worked as well in inner-city regions as it did in intra-city regions. We reviewed the resident population, the number of employees, and the number of SNS posts as variables for generating mass values for an urban traffic gravity model. We also compared the straight-line distance, travel distance, and the impact of time as possible distance values. We defined the functions of urban regions on the basis of public records and SNS data to reflect the diverse social factors in urban regions. In this process, we conducted a dimension reduction method for the public record data and used a machine learning-based clustering algorithm for the SNS data. In doing so, we found that functional distance could be defined as the Euclidean distance between social function vectors in urban regions. Finally, we examined whether the functional distance was a variable that had a significant impact on urban human mobility.

Human mobility prediction is a challenging and crucial task for fostering wide spectrum of location based applications, namely, traffic planning, travel-plan recommendation etc. However, modeling human movement behaviour and predicting next location are non-trivial tasks. We consider the human mobility pattern modeling and predicting next location problem for semantic trajectory data, wherein sparse GPS records are associated with other contextual information. Intuitively, human moves with an intent and the confluence of movement history (GPS traces) and contextual information may help in capturing people's intents at a fine granularity and has potential to improve the efficacy of location prediction problem. In this paper, a hierarchical and layered hidden markov model (HMM) framework for mobility prediction from sparse trajectories has been proposed. Experiment on real-life mobility dataset of Nokia Mobile Data Challenge (MDC) demonstrates the efficacy of the proposed framework even when with sparse GPS traces.

Understanding and predicting mobility are essential for the design and evaluation of future mobile edge caching and networking. Consequently, research on human mobility prediction has drawn significant attention in the last decade. Employing information-theoretic concepts and machine learning methods, earlier research has shown evidence that human behavior can be highly predictable. Whether high predictability manifests itself for different modes of device usage, across spatial and temporal dimensions is still debatable. Despite existing studies, more investigations are needed to capture intrinsic mobility characteristics constraining predictability, to explore more dimensions (e.g. device types) and spatiotemporal granularities, especially with the change in human behavior and technology. We investigate practical predictability of next location visitation across three different dimensions: device type, spatial granularity and temporal spans using an extensive longitudinal dataset, with fine spatial granularity (AP level) covering 16 months. The study reveals device type as an important factor affecting predictability. Ultra-portable devices such as smartphones have "on-the-go" mode of usage (and hence dubbed "Flutes"), whereas laptops are "sit-to-use" (dubbed "Cellos"). The goal of this study is to investigate practical prediction mechanisms to quantify predictability as an aspect of human mobility modeling, across time, space and device types. We apply our systematic analysis to wireless traces from a large university campus. We compare several algorithms using varying degrees of temporal and spatial granularity for the two modes of devices; Flutes vs. Cellos. Through our analysis, we quantify how the mobility of Flutes is less predictable than the mobility of Cellos. In addition, this pattern is consistent across various spatio-temporal granularities, and for different methods (Markov chains, neural networks/deep learning, entropy-based estimators). This work substantiates the importance of predictability as an essential aspect of human mobility, with direct application in predictive caching, user behavior modeling and mobility simulations.

Rapidly developing location acquisition technologies provide a powerful tool for understanding and predicting human mobility in cities, which is very significant for urban planning, traffic regulation, and emergency management. However, with the existing methodologies, it is still difficult to accurately predict millions of peoples’ mobility in a large urban area such as Tokyo, Shanghai, and Hong Kong, especially when collected data used for model training are often limited to a small portion of the total population. Obviously, human activities in city are closely linked with point-of-interest (POI) information, which can reflect the semantic meaning of human mobility. This motivates us to fuse human mobility data and city POI data to improve the prediction performance with limited training data, but current fusion technologies can hardly handle these two heterogeneous data. Therefore, we propose a unique POI-embedding mechanism, that aggregates the regional POIs by categories to generate an artificial POI-image for each urban grid and enriches each trajectory snippet to a four-dimensional tensor in an analogous manner to a short video. Then, we design a deep learning architecture combining CNN with LSTM to simultaneously capture both the spatiotemporal and geographical information from the enriched trajectories. Furthermore, transfer learning is employed to transfer mobility knowledge from one city to another, so that we can fully utilize other cities’ data to train a stronger model for the target city with only limited data available. Finally, we achieve satisfactory performance of human mobility prediction at the citywide level using a limited amount of trajectories as training data, which has been validated over five urban areas of different types and scales.

We aimed to identify the underlying subgroups of the population characterized by distinct lifestyle patterns, and to investigate the associations between lifestyle patterns and risk of incident type 2 diabetes. Using data from the Dutch Lifelines cohort study, latent class analysis was performed to derive lifestyle patterns on five lifestyle factors, i.e., smoking, diet quality, TV watching time, physical activity level, and risk drinking. Associations between lifestyle patterns and incident type 2 diabetes were estimated. Among 61,869 participants analyzed, we identified 900 cases of type 2 diabetes during follow-up (205,696 person-years; incidence rate 4.38 per 1000 person-years). Five lifestyle pattern groups were identified. Using the “healthy lifestyle group” as reference, the “unhealthy lifestyle group” had the highest risk for type 2 diabetes (HR 1.51 [95%CI 1.24, 1.85]), followed by the “poor diet and low physical activity group” (HR 1.26 [95%CI 1.03, 1.55]). The “risk drinker group” and the “couch potato group” (characterized by excessive TV watching) showed no significantly elevated risk. These models were adjusted for age, sex, total energy intake, education, BMI, family history of diabetes, and blood glucose level at baseline. Our study shows that lifestyle factors tended to cluster in unique behavioral patterns within the heterogeneous population. These lifestyle patterns were differentially associated with incident type 2 diabetes. Our findings support the relevance of considering lifestyle patterns in type 2 diabetes prevention. Tailored prevention strategies that target multiple lifestyle risk factors for different lifestyle pattern groups may optimize the effectiveness of diabetes prevention at the population level.

Higher Education is facing disruptive innovation that requires, among other things, provision of a more effective and customized education service to individual students. In the field of Learning Analytics (LA), there has been much effort, in the form ...

Human mobility prediction plays a critical role in applications such as disaster response, urban planning, and epidemic forecasting. Traditional methods often rely on designing crafted, domain-specific models, and typically focus on short-term predictions, which struggle to generalize across diverse urban environments. In this study, we introduce Llama-3-8B-Mob, a large language model fine-tuned with instruction tuning, for long-term citywide mobility prediction---in a Q&A manner. We validate our approach using large-scale human mobility data from four metropolitan areas in Japan, focusing on predicting individual trajectories over the next 15 days. The results demonstrate that Llama-3-8B-Mob excels in modeling long-term human mobility---surpassing the state-of-the-art on multiple prediction metrics. It also displays strong zero-shot generalization capabilities---effectively generalizing to other cities even when fine-tuned only on limited samples from a single city. Source codes are available at https://github.com/TANGHULU6/Llama3-8B-Mob.

BackgroundIntegrated patterns of energy balance-related behaviours of preschool children in Asia are sparse, with few comparative analyses.PurposeUsing cohorts in Singapore (GUSTO) and France (EDEN), we characterized lifestyle patterns of children and investigated their associations with family-focused contextual factors.MethodsTen behavioural variables related to child’s diet, walking, outdoor play and screen time were ascertained by parental questionnaires at age 5–6 years. Using principal component analysis, sex-specific lifestyle patterns were derived independently for 630 GUSTO and 989 EDEN children. Contextual variables were organised into distal (family socio-economics, demographics), intermediate (parental health, lifestyle habits) and proximal (parent-child interaction factors) levels of influence and analysed with hierarchical linear regression.ResultsThree broadly similar lifestyle patterns were identified in both cohorts: “discretionary consumption and high screen time”, “fruit, vegetables, and low screen time” and “high outdoor playtime and walking”. The latter two patterns showed small differences between cohorts and sexes. The “discretionary consumption and high screen time” pattern was consistently similar in both cohorts; distal associated factors were lower maternal education (EDEN boys), no younger siblings (GUSTO boys) and Malay/Indian ethnicity (GUSTO), while intermediate and proximal associated factors in both cohorts and sexes were poor maternal diets during pregnancy, parents allowing high child control over food intake, snacking between meals and having television on while eating.ConclusionsThree similar lifestyle patterns were observed among preschool children in Singapore and France. There were more common associated proximal factors than distal ones. Cohort specific family-focused contextual factors likely reflect differences in social and cultural settings. Findings will aid development of strategies to improve child health.