Category: 3. Business

  • Chinese carmaker Chery to launch fourth brand in UK | Automotive industry

    Chinese carmaker Chery to launch fourth brand in UK | Automotive industry

    The Chinese carmaker Chery is launching a fourth brand in the UK, continuing a push into the British market where it has rapidly become a major player.

    The state-owned company said on Wednesday it would sell cars under the Lepas brand, which is developing battery and hybrid SUVs aimed at younger families, mainly in the European market.

    The decision to add a fourth brand in the UK underlines Chery’s efforts to win market share. The Lepas cars will be built initially in China and imported to the UK, which does not have the tariffs imposed by the US and EU, but the government is hopeful it will eventually decide to manufacture cars in Britain.

    Jaguar Land Rover, Britain’s largest automotive employer, is in early-stage discussions over a potential deal to use its factories to make Chery cars but no agreement has been announced.

    The new brand launch comes a week after Chery said it would open a research and development headquarters in Liverpool for commercial vehicles.

    Chery has been the largest exporter of cars from China for 23 years but did not make significant inroads in Europe because it focused on cheaper models for other regions such as the Middle East.

    The rise of electric cars and heavy government subsidies for Chinese manufacturers, however, have allowed companies such as Chery, BYD and the MG owner SAIC to take on European and Japanese carmakers.

    Chery launched its Omoda brand in 2024, Jaecoo in January 2025 and its eponymous brand last summer. It sold 53,600 of those cars in 2025 in the UK, or 2.7% of the market. That meant it outdid BYD, Tesla and the German-owned Mini, and easily outsold Japanese rivals such as Honda and Mazda.

    In January, Chery sold nearly 6,100 cars in the UK, most of which were hybrids combining a smaller battery with a petrol engine, according to figures from New Automotive, a thinktank.

    The sales figures also suggested that Tesla’s sales slump continued, with only 650 sales recorded, fewer than half the 1,400 recorded in January 2025. The US carmaker’s European sales have been hit by an ageing model lineup as well as consumer distaste for the chief executive Elon Musk’s support for far-right politicians. Tesla’s sales were less than half the 1,326 electric sales of BYD, which last year overtook it to become the world’s biggest seller of battery electric cars.

    Chery has not yet committed to manufacturing in the UK, but it has indicated that it is considering doing so. Its UK director, Victor Zhang, said in June it was “actively considering” building a UK plant as part of a “localisation” strategy.

    The company has said repeatedly it wants to pursue an “in UK, for UK, be UK” strategy, suggesting that setting up manufacturing would be a serious option.

    The Lepas brand – a madeup word referring vaguely to leopards – appears to be positioned as a mass-market offering, emphasising “fun”. Its Jaecoo brand, in contrast, has been described by some as a “Range Rover clone”, albeit for a much cheaper price.

    Continue Reading

  • Stock market today: Live updates

    Stock market today: Live updates

    Traders work on the floor at the New York Stock Exchange (NYSE) in New York City, U.S., Jan. 21, 2026.

    Brendan McDermid | Reuters

    The S&P 500 was relatively unchanged on Wednesday as traders continued to move out of technology stocks and digested the latest labor market data.

    The broad market index hovered around the flatline, while Dow Jones Industrial Average added 259 points, or 0.5%. The Nasdaq Composite dropped 0.6%.

    Shares of Advanced Micro Devices pulled back 12% after its first-quarter forecast underwhelmed some analysts, adding to the recent pressure seen in tech. Other names in the space such as Broadcom and Micron Technology dipped as well. The former was down more than 1%, while the latter fell 3%.

    Software stocks also continued to face pressure, with stocks such as Oracle and CrowdStrike extending their losses from the prior trading day. The two names were both down roughly 3%, as were ServiceNow and Salesforce.

    “Bottom line, something I said back in late November, the GenAI tech trade is no longer a one way ride. We’ve transitioned it from ‘buy everything’ to ‘not everyone can win,’” said Peter Boockvar, chief investment officer at One Point BFG Wealth Partners. “I believe we are losing this trade in terms of its ability to carry the market but luckily so far investors have found other things to buy and that includes other parts of the S&P 500, small and mid cap and for sure international stocks.”

    Amgen was among the names leading the Dow’s outperformance. The biotechnology stock was up 3% after the company reported better-than-expected earnings and revenue for the fourth quarter. Also offering a boost to the index, industrial stock Caterpillar gained 2%, signaling that investors were continuing to rotate into more value-oriented names.

    Meanwhile, ADP on Wednesday released its monthly look at private payroll growth for January, which showed an increase of just 22,000 on the month. That’s below the gain of 45,000 jobs that economists polled by Dow Jones had forecast.

    The release generally precedes the Bureau of Labor Statistics report on nonfarm payrolls, but that won’t be out this week due to the partial government shutdown. The shutdown, which began Saturday, officially ended Tuesday, when President Donald Trump signed a funding bill into law.

    On Tuesday, the major averages sold off as investors gravitated out of riskier growth names and toward cyclical stocks like Walmart. Nvidia and Microsoft each lost almost 3% in the previous session. Big-name artificial intelligence infrastructure names Broadcom, Oracle and Micron also closed in the red. The tech sector was the worst performer in the S&P 500, down more than 2%.

    All eyes are now on Alphabet, as the company is slated to report earnings after the bell Wednesday. The quarterly results of fellow “Magnificent Seven” member Amazon are due Thursday.

    Continue Reading

  • ADP National Employment Report: Private Sector Employment Increased by 22,000 Jobs in January; Annual Pay was Up 4.5% – PR Newswire

    ADP National Employment Report: Private Sector Employment Increased by 22,000 Jobs in January; Annual Pay was Up 4.5% – PR Newswire

    1. ADP National Employment Report: Private Sector Employment Increased by 22,000 Jobs in January; Annual Pay was Up 4.5%  PR Newswire
    2. ADP Report set to show moderate gains in US private-sector employment in January  FXStreet
    3. Private Payrolls Added 22,000 Jobs in January  Barron’s
    4. Private payroll growth in January misses expectations as market awaits official jobs data  Yahoo Finance
    5. Gold prices remain well supported as ADP shows U.S. labor market continuing to cool  KITCO

    Continue Reading

  • Union Pacific and Wabtec Sign $1.2B Deal to Modernize Locomotives

    Union Pacific and Wabtec Sign $1.2B Deal to Modernize Locomotives

    • Largest locomotive modernization agreement in rail industry history
    • Upgrades to significantly improve operational efficiency and fleet productivity

    PITTSBURGH, Feb. 4, 2026 — Union Pacific (NYSE: UNP) and Wabtec (NYSE:WAB) signed a landmark agreement totaling $1.2 billion to modernize the railroad’s AC4400 locomotives. This agreement represents the largest locomotive modernization investment in rail industry history, building on Union Pacific’s previous 2022 order which is scheduled to be completed in 2026. The upgraded fleet will help enhance the railroad’s operational efficiency, service reliability and network performance.

    “We are committed to delivering the service we sold to our customers and one way we do that is having great American-made locomotives that can get the job done,” said Jim Vena, Union Pacific CEO. “These redesigned locomotives will be just like new, providing the improved fuel efficiency and enhanced reliability that we need to grow with our customers and to win new business.”

    Wabtec’s modernization program will extend each locomotive’s useful life, improve fleet standardization and equip Union Pacific to take advantage of next generation control and diagnostics technologies. The upgraded locomotives are expected to deliver over 5% reduction in fuel consumption, a 14% increase in tractive effort and an 80% improvement in reliability.

    “Our continued partnership with Union Pacific reflects a steady, forward-looking investment that positions the railroad and its customers for continued success,” said Rafael Santana, President and CEO of Wabtec. “By enhancing our proven locomotive platforms with advanced propulsion, controls and diagnostics, this program delivers substantial gains in performance, reliability and lifecycle value — allowing the railroad to unlock maximum efficiency and capability for its existing fleet.”

    The modernized locomotives will feature a suite of Wabtec hardware and digital innovations. Each unit will receive the FDL Advantage (FDLA) engine upgrade for enhanced fuel savings; LOCOTROL® Expanded Architecture to support safe, efficient operation of longer trains; and the new Modular Control Architecture, which unlocks the next generation data, diagnostics and software capabilities.

    This agreement, signed in the fourth quarter of 2025, marks Union Pacific’s fourth major modernization order from Wabtec since 2018. Once completed, the railroad will have more than 1,700 modernized locomotives in its fleet. Production will occur at Wabtec’s U.S. facilities, with deliveries beginning in 2027.

    About Wabtec
    Wabtec Corporation (NYSE: WAB) is focused on creating transportation solutions that move and improve the world. The company is a leading global provider of equipment, systems, digital solutions and value-added services for the freight and transit rail industries, as well as the mining, marine and industrial markets. Wabtec has been a leader in the rail industry for over 150 years and has a vision to achieve a more efficient rail system in the U.S. and worldwide. Visit Wabtec’s website at: www.wabteccorp.com.

    About Union Pacific
    Union Pacific (NYSE: UNP) delivers the goods families and businesses use every day with safe, reliable, and efficient service. Operating in 23 western states, the company connects its customers and communities to the global economy. Trains are the most environmentally responsible way to move freight, helping Union Pacific protect future generations. More information about Union Pacific is available at www.up.com.
     

    Continue Reading

  • News | Vietjet selects RTX’s Pratt & Whitney to power 44 additional A320neo family aircraft

    News | Vietjet selects RTX’s Pratt & Whitney to power 44 additional A320neo family aircraft

    Order includes 12-year maintenance agreement

    SINGAPORE, Feb. 4, 2026 /PRNewswire/ — Vietjet Air and Pratt & Whitney, an RTX (NYSE: RTX) business, announce that the airline has selected an additional 44 GTF-powered Airbus A320neo family aircraft, including 24 A321neos and 20 A321XLRs, bringing its total orders to 137 GTF-powered aircraft. Deliveries will start in July 2026. Pratt & Whitney will also provide Vietjet with engine maintenance through a 12-year EngineWise® Comprehensive service agreement.

    Vietjet is a rapidly growing airline with an expansive fleet and flight network. “Vietjet values our relationship with Pratt & Whitney and its latest generation technology,” said Vietjet Managing Director Nguyen Thanh Son. “The GTF engine is powering our growth with industry-leading operating economics and fuel efficiency of up to 20%. We continue to trust in the long-term, comprehensive and responsible partnership with Pratt & Whitney.”

    Based in Ho Chi Minh, Vietnam, Vietjet received its first A321neo aircraft in 2018 and currently operates a fleet of 42 GTF-powered A321neo aircraft. Prior to this order, Vietjet committed to up to 93 aircraft of this type.

    “Ten years ago, Vietjet joined the Pratt & Whitney GTF family and this selection demonstrates the airline’s continued confidence in the GTF engine,” said Rick Deurloo, President of Commercial Engines, Pratt & Whitney. “With this latest order, Vietjet will further realize the benefits of the most efficient engine for single-aisle aircraft and our ongoing commitment to enabling their network expansion.”

    The GTF is the most efficient engine for the single aisle market, delivering up to 20% lower fuel consumption and a 75% smaller noise footprint compared to the prior generation of engines. To date, more than 2,600 GTF-powered aircraft have been delivered to more than 90 customers worldwide. With enhanced payload and range capability, GTF Advantage engine, which is expected to enter into service later this year, will offer a more durable configuration that delivers up to double the time on wing. Pratt & Whitney continues to invest in expanding GTF MRO network capacity and ramping supply chain output to support customers.

    With a modern, flexible fleet and an expanding route network, Vietjet further reaffirms its long-term vision as a multinational aviation group, driving aviation growth and regional economic development. The airline currently operates an extensive Asia-Pacific network, connecting Vietnam and Thailand with Australia, India, Kazakhstan, China, Japan and South Korea, among others, while progressively expanding to destinations in Europe. Vietjet aims to provide the best flying experience at the most competitive cost for passengers through strategic partnerships with leading aviation and technology partners in the industry worldwide.

    About Pratt & Whitney
    Pratt & Whitney, an RTX business, is a world leader in the design, manufacture and service of aircraft engines and auxiliary power units for military, commercial and civil aviation customers. Since 1925, our engineers have pioneered the development of revolutionary aircraft propulsion technologies, and today we support more than 90,000 in-service engines through our global network of maintenance, repair and overhaul facilities.

    About RTX
    With more than 180,000 global employees, we push the limits of technology and science to redefine how we connect and protect our world. With industry-leading capabilities, we advance aviation, engineer integrated defense systems for operational success, and develop next-generation technology solutions and manufacturing to help global customers address their most critical challenges. The company, with 2025 sales of more than $88 billion, is headquartered in Arlington, Virginia.

    About Vietjet
    The new-age carrier Vietjet has not only revolutionized the aviation industry in Vietnam but also been a pioneering airline across the region and around the world. The airline currently operates 135 aircraft and has nearly 600 additional aircraft on order, including both wide-body and narrow-body aircraft. With a focus on cost management ability, effective operations, and performance, applying the latest technology to all activities and leading the trend, Vietjet offers flying opportunities with cost-saving and flexible fares as well as diversified services to meet customers’ demands.

    Vietjet is a fully-fledged member of International Air Transport Association (IATA) with the IATA Operational Safety Audit (IOSA) certificate. As Vietnam’s largest private carrier, the airline has been awarded the highest ranking for safety with 7 stars by the world’s only safety and product rating website airlineratings.com and listed as one of the world’s 50 best airlines for healthy financing and operations by Airfinance Journal in many consecutive years. The airline has also been named as Best Low-Cost Carrier by renowned organizations such as Skytrax, CAPA, Airline Ratings, and many others.

    Media contacts:

    For questions or to schedule an interview, please contact [email protected]

    Vietjet
    Kieu Duong (Amy)
    [email protected]
    +84-932-775-066

    SOURCE RTX

    Continue Reading

  • Major disruption on south-east England rail lines after ‘multiple incidents’

    Major disruption on south-east England rail lines after ‘multiple incidents’

    Disruption affecting one of UK’s busiest railway routespublished at 10:49 GMT

    Thomas Mackintosh
    Live reporter

    Built in the Victorian era, the Brighton Main Line is one of busiest railway routes in the UK.

    It connects the capital with the Sussex coast via Gatwick Airport, serving 37 stations through Sussex, Surrey and south London. It has one terminus station in Sussex – Brighton – and two terminus stations in the capital – London Victoria and London Bridge.

    Both of these London branches join up with the full Brighton Main Line just outside the Selhurst depot.

    That is why this morning’s disruption is so significant as the volume of trains normally using the Brighton Main Line have no other alternative to keep the same flow of services running.

    The trains that have come to a standstill cannot reach their destination and that means drivers and crew are displaced. This has a knock-on impact for further services, leading to the delays and cancellations we are now seeing.

    Continue Reading

  • Global commercial insurance rates fall 4% in Q4 2025, marking the sixth consecutive quarterly decrease

    Global commercial insurance rates fall 4% in Q4 2025, marking the sixth consecutive quarterly decrease

    New York | February 04, 2026

    According to the latest Global Insurance Market Index released today by Marsh Risk, a business of Marsh (NYSE: MRSH) and the world’s leading insurance broker and risk advisor, global commercial insurance rates fell, on average, by 4% in the fourth quarter of 2025. Growing competition among insurers, coupled with a favorable loss environment and reinsurance pricing, were the primary drivers for the rate decline along with increased market capacity.

    With the exception of the US, all global regions experienced year-over-year composite rate decreases in Q4 2025. The Pacific (12%) and India, Middle East, and Africa (IMEA) (10%) regions experienced the largest composite rate decreases, while rates declined in Latin America and the Caribbean (LAC), the UK, and Canada by 7%. Rates declined in Europe and Asia by 6% and 5% respectively. The overall composite rate in the US – which declined by 1% in Q3 2025 – was flat in Q4.

    Q4 marks the sixth consecutive global quarterly decreases following seven years of quarterly increases and is a continuation of the moderating rate trend first recorded in Q1 2021.

    Other findings included:

    • Property rates declined by 9% globally, following an 8% decline in Q3. Four regions – the Pacific (14%), LAC (12%), IMEA (11%), and the UK (10%) – recorded double-digit decreases, while the US, Canada, and Europe declined by 8%, and Asia by 5%.
    • Casualty rates increased 4% globally – up from a 3% increase in Q3 – which was driven by a 9% increase in the US (8% in Q3) due largely to the continued concerns among insurers about the frequency and severity of casualty claims, many of which are characterized by large (so-called “nuclear”) jury awards.
    • Financial and professional lines rates decreased by 4% globally in the fourth quarter, compared to a 5% decrease in Q3. Rate declines were recorded across most regions – barring the US – ranging from 11% in IMEA to 5% in the UK and Canada. Financial and professional insurance rates in the US were flat as compared to a 2% decline in Q3.
    • Cyber insurance rates decreased by 7% globally, with declines seen in every region ranging from 14% in LAC  to 3% in the US.

    Commenting on the report, John Donnelly, President, Global Placement, Marsh Risk, said: “The global insurance market has been characterized by ample capacity across most lines and regions over the last six quarters. In the absence of unforeseen circumstances we expect this trend to continue throughout 2026. This year, clients have the opportunity to secure reduced premium rates and negotiate broader terms which may include improving the resilience of their programs to cater for the increasing complexity of risks.”

    Continue Reading

  • With caviar McNuggets and heart-shaped pizza, fast food chains hope to win Valentine’s diners

    With caviar McNuggets and heart-shaped pizza, fast food chains hope to win Valentine’s diners

    It’s a tale as old as time, or at least as old as TikTok: chicken nuggets lovingly topped with a dab of caviar.

    McDonald’s is embracing the trend this Valentine’s Day with a limited-time McNugget Caviar kit. The free kit, which will be available on McNuggetCaviar.com on Feb. 10, pairs a one-ounce tin of Paramount’s Siberian sturgeon caviar with a $25 McDonald’s gift card to buy McNuggets. McDonald’s is even throwing in some crème fraiche and a caviar spoon.

    Valentine’s Day is big business for U.S. restaurants. It’s the second-most popular holiday for dining out after Mother’s Day, according to the National Restaurant Association.

    Casual, sit-down restaurants see the biggest lift in traffic, especially when Valentine’s Day is on a weekday, according to Circana, a market research firm. Fast-food restaurants see less of a bump in sales. But McDonald’s is one of several fast-food chains hoping to change that with special promotions or products.

    For the 35th year in a row, White Castle is transforming its restaurants into Love Castles, with hostess seating, tableside service and Valentine’s Day décor. White Castle said some of the 300 participating restaurants are already booked for the night.

    Nugget lovers can get their orders in a heart-shaped tray from Chick-fil-A. Papa Johns and Pizza Hut offer heart-shaped pizzas, while Auntie Anne’s has a heart-shaped soft pretzel. Jack in the Box is giving away heart-shaped straws and Hardee’s is making heart-shaped biscuits. Even 7-Eleven is getting in on the action, offering heart-shaped donuts and $14 off delivery orders.

    McDonald’s said it got the idea for caviar McNuggets from fans, who have been rhapsodizing about the high-low pairing for years on social media. Celebrity chef David Chang has posted many times about his love for caviar on fried chicken and Popeyes biscuits. In 2024, the pop star Rihanna downed caviar and chicken nuggets in a TikTok video.

    McDonald’s wouldn’t say how many kits it will distribute, but said supplies are limited. That’s no surprise: a one-ounce tin of Siberian sturgeon caviar costs $85 on Paramount’s website, or about the cost of 166 Chicken McNuggets.

    Continue Reading

  • GSK delivers strong 2025 performance and re-affirms long-term outlooks

    GSK delivers strong 2025 performance and re-affirms long-term outlooks

    Luke Miels, Chief Executive Officer, GSK:

    “GSK delivered another strong performance in 2025, driven mainly by Specialty Medicines, with double-digit sales growth in 
    Respiratory, Immunology & Inflammation (RI&I), Oncology and HIV. Good R&D progress also continued, with 5 major product 
    approvals achieved and several acquisitions and new partnerships completed to strengthen the pipeline further in oncology and RI&I. We expect this positive momentum to continue in 2026, which will be a key year of execution and operational delivery with strong focus on commercial launches and accelerating R&D. We are well placed to move forward in this next phase for GSK – to deliver our outlooks – and to create new value for patients and shareholders.”

    Assumptions and cautionary statement regarding forward-looking statements

    The Group’s management believes that the assumptions outlined above are reasonable, and that the guidance, 
    outlooks, and expectations described in this report are achievable based on those assumptions. However, given the 
    forward-looking nature of these guidance, outlooks, and expectations, they are subject to greater uncertainty, including 
    potential material impacts if the above assumptions are not realised, and other material impacts related to foreign 
    exchange fluctuations, macro-economic activity, the impact of outbreaks, epidemics or pandemics, changes in 
    legislation, regulation, government actions and policies, including the impact of any potential tariffs or other restrictive 
    trade policies on the Group’s products, or intellectual property protection, product development and approvals, actions 
    by our competitors, and other risks inherent to the industries in which we operate.

    This document contains statements that are, or may be deemed to be, “forward-looking statements”. Forward-looking 
    statements give the Group’s current expectations or forecasts of future events. An investor can identify these 
    statements by the fact that they do not relate strictly to historical or current facts. They use words such as ‘anticipate’, 
    ‘estimate’, ‘expect’, ‘intend’, ‘will’, ‘project’, ‘plan’, ‘believe’, ‘target’, ‘outlook’, ‘aim’, ‘ambition’, ‘could’, ‘goal’, ‘may’, 
    ‘seek’, ‘should’ and other words and terms of similar meaning in connection with any discussion of future operating or 
    financial performance. In particular, these include statements relating to future actions, prospective products or 
    product approvals, future performance or results of current and anticipated products, sales efforts, expenses, the 
    outcome of contingencies such as legal proceedings, dividend payments and financial results. Other than in 
    accordance with its legal or regulatory obligations (including under the Market Abuse Regulation, the UK Listing Rules 
    and the Disclosure Guidance and Transparency Rules of the Financial Conduct Authority), the Group undertakes no 
    obligation to update any forward-looking statements, whether as a result of new information, future events or 
    otherwise. The reader should, however, consult any additional disclosures that the Group may make in any documents 
    which it publishes and/or files with the SEC. All readers, wherever located, should take note of these disclosures. 
    Accordingly, no assurance can be given that any particular expectation will be met and readers are cautioned not to 
    place undue reliance on the forward-looking statements.

    All guidance, outlooks and expectations should be read together with the guidance and outlooks, assumptions and 
    cautionary statements in this full year and Q4 2025 earnings release and in the Group’s 2024 Annual Report on Form 
    20-F.

    Forward-looking statements are subject to assumptions, inherent risks and uncertainties, many of which relate to 
    factors that are beyond the Group’s control or precise estimate. The Group cautions investors that a number of 
    important factors, including those in this document, could cause actual results to differ materially from those expressed 
    or implied in any forward-looking statement. Such factors include, but are not limited to, those discussed under ‘Risk 
    Factors’ in the Group’s Annual Report on Form 20-F for 2024. Any forward-looking statements made by or on behalf of 
    the Group speak only as of the date they are made and are based upon the knowledge and information available to 
    the Directors on the date of this report.

    Continue Reading

  • Liu, Y., James, J. Q., Kang, J., Niyato, D. & Zhang, S. Privacy-preserving traffic flow prediction: A federated learning approach. IEEE Internet Things J. 7 (8), 7751–7763. https://doi.org/10.1109/JIOT.2020.2974820 (2020).

    Google Scholar 

  • Peng, H. et al. Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning. Inf. Sci. 578, 401–416. https://doi.org/10.1016/j.ins.2021.06.053 (2021).

    Google Scholar 

  • Djenouri, Y., Belhadi, A., Srivastava, G. & Lin, J. C. W. Hybrid graph convolution neural network and branch-and-bound optimization for traffic flow forecasting.Future Generation Comput. Syst. 139: 100–108. https://doi.org/10.1016/j.future.2022.09.032. (2023).

  • Williams, B. M. & Hoel, L. A. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results. Journal of Transportation Engineering 129(6), 664–672. https://doi.org/10.1061/(ASCE)0733-947X (2003).

  • Zhang, Q., Li, C., Su, F. & Li, Y. Spatiotemporal residual graph attention network for traffic flow forecasting. IEEE Internet Things J. 10 (13), 11518–11532. https://doi.org/10.1109/JIOT.2023.3248874 (2023).

    Google Scholar 

  • Yu, B., Yin, H. & Zhu, Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting.Proceedings of the 27th International Joint Conference on Artificial Intelligence. 3634–3640. https://doi.org/10.24963/ijcai.2018/505 (2018).

  • Li, Y., Yu, R., Shahabi, C. & Liu, Y. Diffusion convolutional recurrent neural network: data-driven traffic forecasting. InternationalConference on Learning Representations (ICLR 2018). Vancouver, Canada. https://doi.org/10.48550/arXiv.1707.01926 (2018).

  • Cai, L., Janowicz., K., Mai., G., Yan., B. & Zhu, R. Traffic transformer: capturing the continuity and periodicity of time series for traffic forecasting. Trans. GIS. 24 (3), 736–755. https://doi.org/10.1111/tgis.12644 (2020).

    Google Scholar 

  • Liu, H. et al. STAEformer: Spatio-Temporal adaptive embedding makes vanilla transformer SOTA for traffic forecasting. Proc. 32nd ACM Int. Conf. Inform. Knowl. Manage. (CIKM). 4125-4129 https://doi.org/10.48550/arXiv.2308.10425 (2023).

  • Kazemi, S. M. et al. Representation learning for dynamic graphs: A survey. J. Mach. Learn. Res. 21 (70), 1–73 (2020).

    Google Scholar 

  • Zhao, L. et al. T-GCN: A Temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21 (9), 3848–3858. https://doi.org/10.1109/TITS.2019 (2019).

    Google Scholar 

  • Peng, H. et al. Spatial Temporal incidence dynamic graph neural networks for traffic flow forecasting. Inf. Sci. 521, 277–290. https://doi.org/10.1016/j.ins.2020.02.006 (2020).

    Google Scholar 

  • Vaswani, A. et al. Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 1–11 (2017).

    Google Scholar 

  • Cai, L., Janowicz, K., Mai, G., Yan, B. & Zhu, R. Traffic transformer: capturing the continuity and periodicity of time series for traffic forecasting. Trans. GIS. 24 (3), 736–755. https://doi.org/10.1111/tgis.12607 (2020).

    Google Scholar 

  • Zheng, C. et al. Spatio-temporal joint graph convolutional networks for traffic forecasting. IEEE Trans. Knowl. Data Eng. 36 (1), 372–385. https://doi.org/10.1109/TKDE.2022 (2023).

    Google Scholar 

  • Han, L., Du, B., Sun, L., Fu, Y. & Lv, Y. and H. Dynamic and multi-faceted spatio-temporal deep learning for traffic speed forecasting. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 547–555 https://doi.org/10.1145/3447548.3467118 (2021).

  • Kong, J., Fan, X., Zuo, M., Deveci, M., Zhong, K. & X., and ADCT-Net: adaptive traffic forecasting neural network via dual-graphic cross-fused transformer. Inform. Fusion. 103, 102122. https://doi.org/10.1016/j.inffus.2023.102122 (2024).

    Google Scholar 

  • Wu, C. H., Ho, J. M. & Lee, D. T. Travel-time prediction with support vector regression. IEEE Trans. Intell. Transp. Syst. 5 (4), 276–281. https://doi.org/10.1109/TITS.2004.837813 (2004).

    Google Scholar 

  • Liu, A. & Zhang. Y Spatial–Temporal dynamic graph convolutional network with interactive learning for traffic forecasting. IEEE Trans. Intell. Transp. Syst. 25 (7), 7645–7660. https://doi.org/10.1109/TITS.2024.3362145 (2024).

    Google Scholar 

  • Wu, Y., Tan, H., Qin, L., Ran, B. & Jiang, Z. A hybrid deep learning based traffic flow prediction method and its Understanding. Transp. Res. Part. C: Emerg. Technol. 90, 166–180. https://doi.org/10.1016/j.trc.2018.03.001 (2018).

    Google Scholar 

  • Li, M. & Zhu, Z. Spatial-temporal fusion graph neural networks for traffic flow forecasting. Proceedings of the AAAI Conference on Artificial Intelligence 35(5), 4189–4196 https://doi.org/10.1609/aaai.v35i5.16550 (2021).

  • Fang, Z., Long, Q. & Song, G. and K. Spatial-temporal graph ODE networks for traffic flow forecasting. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining: 364–373. (2021). https://doi.org/10.1145/3447548.3467141

  • Xu, Y. et al. Generic dynamic graph convolutional network for traffic flow forecasting. Inform. Fusion. 100, 101946. https://doi.org/10.1016/j. inffus.2023.101946 (2023).

    Google Scholar 

  • Fang, Y., Zhao, F., Qin, Y., Luo, H. & Wang, C. Learning all dynamics: traffic forecasting via locality-aware spatio-temporal joint transformer. IEEE Trans. Intell. Transp. Syst. 23 (12), 23433–23446. https://doi.org/10.1109/TITS.2022 (2022).

    Google Scholar 

  • Lin, L., Li, W., Bi, H. & Qin, L. Vehicle trajectory prediction using LSTMs with spatial-temporal attention mechanisms. IEEE Intell. Transp. Syst. Mag. 14 (2), 197–208. https://doi.org/10.1109/MITS.2021.3058034 (2021).

    Google Scholar 

  • Guo, S., Lin, Y., Wan, H., Cong, G. & L., and Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting. IEEE Trans. Knowl. Data Eng. 34 (11), 5415–5428. https://doi.org/10.1109/TKDE.2021.3081562 (2021).

    Google Scholar 

  • Zhu, J. et al. KST-GCN: A knowledge-driven spatial-temporal graph convolutional network for traffic forecasting. IEEE Trans. Intell. Transp. Syst. 23 (9), 15055–15065. https://doi.org/10.1109/TITS.2021.3137177 (2022).

    Google Scholar 

  • Kong, X., Wang, K., Hou, M., Karmakar, F., Li, J. & G., and Exploring human mobility for multi-pattern passenger prediction: A graph learning framework. IEEE Trans. Intell. Transp. Syst. 23 (9), 16148–16160. https://doi.org/10.1109/TITS.2021 (2022).

    Google Scholar 

  • Chen, Y., Segovia, I. & Gel, Y. R. Z-GCNETs: Time zigzags at graph convolutional networks for time series forecasting. Proceedings of the 38th International Conference on Machine Learning 139: 1684–1694. (2021).

  • Lee, K. & Rhee, W. DDP-GCN: Multi-graph convolutional network for Spatiotemporal traffic forecasting. Transp. Res. Part. C: Emerg. Technol. 134, 103466. https://doi.org/10.1016/j.trc.2021.103466 (2022).

    Google Scholar 

  • Shin, Y. & Yoon, Y. Incorporating dynamicity of transportation network with multi-weight traffic graph convolutional network for traffic forecasting. IEEE Trans. Intell. Transp. Syst. 23 (3), 2082–2092. https://doi.org/10.1109/TITS.2021 (2022).

    Google Scholar 

  • Bai, L., Yao, L., Li, C., Wang, X. & Wang, C. Adaptive graph convolutional recurrent network for traffic forecasting. Adv. Neural. Inf. Process. Syst. 33, 17804–17815 (2020).

    Google Scholar 

  • Wu, Z., Pan, S., Long, G., Jiang, J. & Zhang, C. Graph WaveNet for deep spatial-temporal graph modeling. Proceedings of the 28th International Joint Conference on Artificial Intelligence: 1907–1913. (2019). https://doi.org/10.24963/ijcai.2019/264

  • Wang, W. D. P. K. Spatial–Temporal graph attention gated recurrent transformer network for traffic flow forecasting. IEEE Internet Things J. 11 (8), 14267–14281. https://doi.org/10.1109/JIOT.2023.3340182 (2024).

    Google Scholar 

  • Shin, Y. & Yoon. Y PGCN: progressive graph convolutional networks for Spatial-Temporal traffic forecasting. IEEE Trans. Intell. Transp. Syst. 25 (7), 7633–7644. https://doi.org/10.1109/TITS.2024.3349565 (2024).

    Google Scholar 

  • Fang, Y. et al. Efficient large-scale traffic forecasting with transformers: A Spatial data management perspective. KDD ‘25: Proc. 31st ACM SIGKDD Conf. Knowl. Discovery Data Min. 307-317 https://doi.org/10.1145/3690624.3709177 (2024).

  • Fang, Y. et al. Unraveling spatio-temporal foundation models via the pipeline lens: A comprehensive review. Inf. Fusion. 115, 102346. https://doi.org/10.48550/arXiv.2506.01364 (2025).

    Google Scholar 

  • Yang., S., Wu., Q., Wang., Y. & Lin, T. SSGCRTN: A space-specific graph convolutional recurrent transformer network for traffic prediction. Appl. Intell. 54 (22), 11978–11994. https://doi.org/10.1007/s10489-024-05815-1 (2024).

    Google Scholar 

  • Yang., S., Huang., Z., Wu., Q. & Zhuo, Z. MSTDFGRN: A multi-view spatio-temporal dynamic fusion graph recurrent network for traffic flow prediction. Comput. Electr. Eng. 123, 110046. https://doi.org/10.1016/j.compeleceng.2024.110046 (2025).

    Google Scholar 

  • Yang, S., Wu, Q., Li, Z. & Wang, K. PSTCGCN: principal spatio-temporal causal graph convolutional network for traffic flow prediction. Neural Comput. Appl. 1-14, https://doi.org/10.1007/s00521-024-10769-6 (2024).

  • Yang., S., Wu., Q., Li., M. & Sun, Y. Temporal identity interaction dynamic graph convolutional network for traffic forecasting. IEEE Internet Things J. 12 (11), 15057–15072. https://doi.org/10.1109/JIOT.2025.3503328 (2025).

    Google Scholar 

  • Yang., S. & Wu, Q. SDSINet: A Spatiotemporal dual-scale interaction network for traffic prediction. Appl. Soft Comput. 112892. https://doi.org/10.1016/j.asoc.2025.112892 (2025).

    Google Scholar 

  • Yang., S. & Wu, Q. MTEGCRN: Multi-scale Temporal enhanced graph convolutional recurrent network for traffic prediction. Neurocomputing 131064 https://doi.org/10.1016/j.neucom.2025.131064 (2025).

  • Yang., S., Wu., Q., Huang., Z. & Zhuo, Z. General Decoupled Graph Convolutional Recurrent Network for Traffic Prediction. IEEE Sensors J. (2025).

  • Yang., S., Wu., Q. & Li, M. Decoupled Multi-Spatio-Temporal Fusion Graph Convolutional Recurrent Network for Traffic Prediction. Eng. Appl. Artif. Intell. 163: 112956. https://doi.org/10.1016/j.engappai.2025.112956. (2025).

  • Guo, S., Lin, Y., Feng, N., Song, C. & Wan, H. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. Proceedings of the AAAI Conference on Artificial Intelligence 33(01): 922–929. (2019). https://doi.org/10.1609/aaai.v33i01. 3301922.

  • Lan, S., Huang, M. Y., Wang, W., Yang, W. & Li, H. P. DSTAGNN: Dynamic spatial-temporal aware graph neural network for traffic flow forecasting. in: International Conference on Machine Learning, PMLR, 11906–11917. (2022).

  • Li, J. D. S. J. W. R. & Huang, Y. Y., Yang. Y.-B. Trafformer: unify time and space in traffic prediction. in: Proceedings of the AAAI Conference on Artificial Intelligence, 37(7): 8114–8122. (2023).

  • Shao, Z., Zhang, Z., Wang, F., Wei, W. & Xu, Y. Spatial-temporal identity: A simple yet effective baseline for multivariate time series forecasting. Proceedings of the 31st ACM International Conference on Information & Knowledge Management: 4454–4458. (2022). https://doi.org/10.1145/3511808.3557410

  • Cui, Z., Henrickson, K., Ke, R. & Wang, Y. Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting. IEEE Trans. Intell. Transp. Syst. 21 (11), 4883–4894. https://doi.org/10.1109/TITS.2019.2950416 (2020).

    Google Scholar 

  • Pan, Z. et al. Spatio-temporal meta learning for urban traffic prediction. IEEE Trans. Knowl. Data Eng. 34 (3), 1462–1476. https://doi.org/10.1109/TKDE.2020.2989138 (2020).

    Google Scholar 

  • Chen, C., Liu, Y., Chen, L. & Zhang, C. Bidirectional spatial-temporal adaptive transformer for urban traffic flow forecasting. IEEE Trans. Neural Networks Learn. Syst. 34 (10), 6913–6925. https://doi.org/10.1109/TNNLS.2022.3156673 (2022).

    Google Scholar 

  • Al-Huthaif, R., Li, T., Al-Huda, Z. & Li, C. FedAGAT: Real-time traffic flow prediction based on federated community and adaptive graph attention network. Inf. Sci. 667 (2024), 120482. https://doi.org/10.1016/j.ins.2024.120482 (2024).

    Google Scholar 

  • Lai, Q. & Chen, P. LEISN: A long explicit-implicit spatio-temporal network for traffic flow forecasting. Expert Syst. Appl. 245 (2024), 123139. https://doi.org/10.1016/j.eswa.2024.123139 (2024).

    Google Scholar 

  • Wang., R., Xi., L., Ye., J., Zhang., F. & Xu, X. Y. L. Adaptive Spatio-Temporal relation based transformer for traffic flow prediction. IEEE Trans. Veh. Technol. 74 (2), 2220–2230. https://doi.org/10.1109/TVT.2024.3390997 (2025).

    Google Scholar 

  • Fan., J., Weng., W., Chen., Q., Wu., H. & Wu, J. Pdg2seq: periodic dynamic graph to sequence model for traffic flow prediction. Neural Netw. 183, 106941. https://doi.org/10.1016/j.neunet.2024.106941 (2025).

    Google Scholar 

  • Wu, B. et al. DT-CTFP: 6 g-enabled digital twin collaborative traffic flow prediction. IEEE Trans. Intell. Transp. Syst. 26 (10), 18129–18144. https://doi.org/10.1109/TITS.2025.3582356 (2025).

    Google Scholar 

Continue Reading