CL Changjian Liu Spatial x Causal x Decision

Academic Homepage · Spatial Intelligence

Changjian Liu

Spatial Intelligence / Causal Inference / Decision Systems

I build learning systems for spatial intelligence, causal response estimation, and industrial decision-making. My work connects spatio-temporal big data, GeoAI, advertising algorithms, uplift modeling, and causal inference, with a focus on stable response laws under observational and non-stationary settings.

View Publications Read Research Notes
Email GitHub Google Scholar
Core field Spatial Intelligence
Decision layer Causal response learning
Applied systems Pricing, uplift, allocation

News

Latest updates

All news

Homepage rebuilt with Astro

The personal homepage has moved from hand-written static HTML to a typed Astro, React, and Three.js architecture.

WebsiteAstroDesign

Visitor analytics map roadmap

A country-level visitor heatmap is being added with a privacy-preserving Cloudflare Workers and D1 backend.

AnalyticsCloudflareVisualization

Homepage Earth visual refresh

The old standalone Earth demo is being folded into a cleaner homepage background using a satellite-textured globe.

Spatial IntelligenceHomepageThree.js

Blog

Research notes

All posts

Research Notes

Stable Response Estimation Under Temporal Drift

A research note on why observational response models become brittle when logs, policies, and environments move together.

causal inferenceuplift modelingtemporal drift

Design Notes

Designing a Spatial Intelligence Homepage

How the homepage visual language can signal spatial intelligence without turning the site into a heavy demo page.

spatial intelligencevisual designthree.js

About

Researcher profile

I am currently pursuing my master's degree in Spatio-Temporal Big Data at Peking University, after completing my bachelor's degree in Computer Science and Technology at China University of Geosciences, Beijing.

My academic background sits at the intersection of spatial intelligence and modern machine learning. On the application side, I work on industrial decision systems, including pricing, advertising optimization, and causal decision-making.

Research

Research directions

Methods that connect spatial structure, response estimation, and real decisions.

GeoAI

Spatial Intelligence

Spatio-temporal prediction, trajectory modeling, graph neural networks, spatial flow, and explainable spatial regression.

GeoAImobility flowtrajectory modeling

uplift

Causal Response Learning

Stable treatment-response estimation from non-stationary observational logs, orthogonal learning, and decision-oriented causal modeling.

upliftorthogonal learningnon-stationarity

pricing

Industrial Decision Systems

Pricing, budget allocation, multi-treatment optimization, and robust policy design for online platforms.

pricingallocationpolicy optimization

Publications

Publications (representative papers are highlighted)

Last update: Jun 2026

Full list on Google Scholar
Figure from the trajectory semantic model paper, showing spatial dependence modelling and temporal dependence modelling.

Integrating trajectory data and demographic characteristics: a trajectory semantic model for predicting travel flow and conducting interaction analysis

Changjian Liu, Shuhui Gong, Hui Su, Jianwei Chen, Honglei Guo, Jifeng He, Changfeng Jing, Yu Liu

International Journal of Digital Earth 17(1), 2392842 · 2024 · First Author

A trajectory semantic modeling framework that combines movement traces with demographic structure for travel-flow prediction and interaction analysis.

graph neural networksspatio-temporal predictionmobility flow modeling
webpage pdf scholar
Figure 1 from the photovoltaic power forecasting paper, showing the workflow and schematic diagram of the proposed model.

High precision prediction of time-varying photovoltaic power based on dynamic adjacency matrix and temporal spectral graph convolution network

Honglei Guo, Zhenchan Su, Zhiwei Wang, Guiren Zhan, Changjian Liu, Ling Bu

Energy Conversion and Management: X 30, 101676 · 2026 · Co-Author

A dynamic graph forecasting model for time-varying photovoltaic power prediction under volatile renewable-energy generation patterns.

graph neural networksphotovoltaic forecastingdynamic adjacency
webpage scholar
Figure from the VisitFrequency-Diffusion paper, showing diffusion-based trajectory generation and trajectory refinement.

VisitFrequency-Diffusion: Leveraging Recurrent Visits for Long-Term Individual Trajectory Forecasting

Ziyan Yang, Shuhui Gong, Xinqi Liu, Jiahao Lv, Changjian Liu, Jilin Hu, Hongbin Pei

Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems, 1190-1193 · 2025 · Co-Author

A generative trajectory forecasting study that uses recurrent visit patterns to improve long-horizon individual mobility prediction.

generative modelinghuman mobilitylong-horizon trajectory forecasting
webpage pdf scholar

Experience

Decision systems in practice

2025.11 - Present

Alibaba / Alimama

Worked on managed marketing pricing and ad-equity uplift modeling for advertising decision systems.

  • Participated in cost optimization and downstream allocation design.
  • Connected pricing response models with decision-facing evaluation.

2025.06 - 2025.10

Didi Chuxing

Modeled short-term LTV under coupon-package interventions and optimized personalized allocation under budget constraints.

  • Built personalized treatment allocation logic for coupon packages.
  • Online A/B test reported +6% purchase rate and +3% ROI.

Visitor Analytics

Global research reach

Country-level visitor aggregation for the academic homepage. The production path uses a Cloudflare Worker and D1, while this static build remains publishable with fallback data.

1,284Total visits
12Countries
FallbackData source
No visits yetNo visits yetNo visits yet62 visits302 visitsNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yet12 visitsNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yet44 visitsNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yet39 visitsNo visits yet31 visitsNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yet75 visitsNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yet51 visitsNo visits yet368 visitsNo visits yetNo visits yetNo visits yet94 visitsNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yet88 visitsNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yetNo visits yet
Updated Jun 12, 2026Country-level only · No IP storage

References

Academic sites worth learning from

A small reference board for future homepage design iterations.

Jon Barron Dense but readable research list with clear project and paper links. Deepak Pathak Practical News section paired with representative publications. Lilian Weng Strong model for long-form research notes and technical writing. Carl Vondrick Clean academic structure with easy scanning across research outputs. Andrej Karpathy Minimal personal brand and concise entry points to deeper content. Keunhong Park Modern young-researcher homepage with portfolio-like clarity.