ARXIV:2605.14855 · FORECASTING · SUBMITTED 15 MAY · 20:12 UTC · FRESHNESS FRESH

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers

Lukas Schelenz · Shobha Rajanna · Denis Gosalci · Lucas Heublein · Jonas Pirkl · Jonathan Ott · +3 at arXiv

A hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports.

Ship in 2-4 weeks›Score6.0Evidence unverified

Opportunity summary

Pain A hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports.

Evidence 0 refs | 0 sources | 0% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports. This task poses significant challenges due to the inherently interactive and unpredictable nature of sports, where…

METHOD

Full abstract

Forecasting within signal processing pipelines is crucial for mitigating delays, particularly in predicting the dynamic movements of objects such as NBA players. This task poses significant challenges due to the inherently interactive and unpredictable nature of sports, where abrupt changes in velocity and direction are prevalent. Traditional approaches, including (S)ARIMA(X), Kalman filters (KF), and Particle filters (PF), often struggle to model the non-linear dynamics present in such scenarios. Machine learning (ML) methods, such as long short-term memory (LSTM) networks, graph neural networks (GNNs), and Transformers, offer greater flexibility and accuracy but frequently fail to explicitly capture the interplay between temporal dependencies and contextual interactions, which are critical in chaotic sports environments. In this paper, we evaluate these models and assess their strengths and weaknesses. Experimental results reveal key performance trade-offs across input history length, generalizability, and the ability to incorporate contextual information. ML-based methods demonstrated substantial improvements over linear models across forecast horizons of up to 2s. Among the tested architectures, our hybrid LSTM augmented with contextual information achieved the lowest final displacement error (FDE) of 1.51m, outperforming temporal convolutional neural network (TCNN), graph attention network (GAT), and Transformers, while also requiring less data and training time compared to GAT and Transformers. Our findings indicate that no single architecture excels across all metrics, emphasizing the need for task-specific considerations in trajectory prediction for fast-paced, dynamic environments such as NBA gameplay.

RESULT

ScienceToStartup currently rates this 6.0/10 on the public viability pass. Experimental results reveal key performance trade-offs across input history length, generalizability, and the ability to incorporate contextual information. Code availability is flagged in the…

WHY NOW

Forecasting moved forward this cycle; last verified May 2026. Public score 6.0/10. Production flags indicate code availability.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score6.0

PainA hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports.

Evidence0 refs | 0 sources | 0% coverage

Blockerno shell-level blocker reported

Analysis summary

A hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Competitive landscape

A hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports.

Segment

Forecasting

Adoption evidence

No public code link in the paper record yet

Commercial read

6.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "94d54fc5-f733-4f48-af62-f07003794139", "arxiv_id": "2605.14855", "canonical_route": "/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n", "endpoints": { "paper_pack": "/api/v1/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n/paper-pack", "build_passport": "/api/v1/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers", "normalized_query": "2605.14855", "route": "/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n", "paper_ref": "exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n#webpage", "url": "https://sciencetostartup.com/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n", "name": "Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers", "description": "A hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n#scholarlyArticle", "headline": "Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers", "description": "A hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports.", "url": "https://sciencetostartup.com/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n", "sameAs": "https://arxiv.org/abs/2605.14855", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2605.14855" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-05-14T14:02:45.000Z", "author": [ { "@type": "Person", "name": "Lukas Schelenz" }, { "@type": "Person", "name": "Shobha Rajanna" }, { "@type": "Person", "name": "Denis Gosalci" }, { "@type": "Person", "name": "Lucas Heublein" }, { "@type": "Person", "name": "Jonas Pirkl" }, { "@type": "Person", "name": "Jonathan Ott" }, { "@type": "Person", "name": "Felix Ott" }, { "@type": "Person", "name": "Christopher Mutschler" }, { "@type": "Person", "name": "Tobias Feigl" } ], "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 6 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "Forecasting" }, { "@type": "PropertyValue", "propertyID": "commercialReadiness", "value": "code" } ] }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "Forecasting", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "Exploitation of Hidden Context in Dynamic Movement Forecasti", "item": "https://sciencetostartup.com/paper/exploitation-of-hidden-context-in-dynamic-movement-forecasting-a-neural-network-journey-from-recurrent-to-graph-neural-n" } ] } ] }

Competitive landscape

A hybrid LSTM model augmented with contextual information outperforms other ML architectures for dynamic movement forecasting in sports.

Segment

Forecasting

Adoption evidence

No public code link in the paper record yet

Commercial read

6.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers

Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline