Using Large Action Model (LAM) trained on time-series data obtained from various customer touchpoints, such as online and in-store interactions, NTT and DOCOMO have achieved personalized 1-to-1 marketing tailored to each customer’s individual needs.The research and development of LAM was led by NTT. By pre-learning patterns in behavioral sequences from customer time-series data to predict customers’ intent, and then further learning the content, method, timing, and effectiveness of promotional measures to personalize them, the model was designed to flexibly accommodate diverse promotional strategies.DOCOMO was responsible for integrating customer data into the “4W1H” format (Who, When, Where, What, and How), constructing the LAM, and verifying the effectiveness of promotional measures. As a result, telemarketing orders for mobile and smart life-related services increased by up to 2 times compared to conventional methods.TOKYO, Nov 12, 2025 - (JCN Newswire via SeaPRwire.com) - NTT, Inc. (Headquarters: Chiyoda-ku, Tokyo; President and CEO: Akira Shimada; hereinafter "NTT") and NTT DOCOMO, INC. (Headquarters: Chiyoda-ku, Tokyo; President and CEO: Yoshiaki Maeda; hereinafter "DOCOMO") have established a new AI technology called the Large Action Model (LAM) which predicts customers’ intent based on time-series data organized in the “4W1H” format (Who, When, Where, What, and How) collected from various customer touchpoints, including online channels and physical stores. This technology enables highly personalized 1-to-1 marketing tailored to each customer’s needs. LAM is a generative AI technology specialized for time-series data that includes both numerical and categorical data, possessing a structure similar to large language models (LLMs).NTT was responsible for the research, development, and tuning of the model, while DOCOMO handled the integration of customer data, the construction of the LAM, and the verification of the promotional effectiveness.*1 As a result, the order rate for mobile and smart life-related services through telemarketing improved by up to 2 times compared with conventional methods.Furthermore, through innovations in design and parameter optimization, DOCOMO’s proprietary LAM was successfully built using less than one day of computation, equivalent to approximately 145 GPU hours, on a GPU server equipped with eight NVIDIA A100 (40GB) units.The research results will be exhibited at NTT R&D FORUM 2025 IOWN ∴Quantum Leap*2, to be held from November 19 to 26, 2025.Figure 1 Overview of the initiativeBackground and Challenges in Advancing MarketingAs companies aim to enhance customer satisfaction and create new revenue opportunities, advancing marketing strategies has become a key challenge. Until recently, most companies relied on “segment marketing,” which groups customers based on attributes such as age or gender and provides tailored proposals to each group. In recent years, however, “1-to-1 marketing,” which offers personalized proposals for each individual customer, has been gaining attention, creating a need for more precise customer understanding.To effectively implement 1-to-1 marketing, it is essential to utilize sequential behavioral data obtained from various daily customer touchpoints and to understand customer needs based on the entire process leading up to product purchases or service subscriptions, known as the customer journey. However, because the frequency and format of data differ across touchpoints, integrating and analyzing time-series data has been technically challenging. For example, app usage generates high-frequency operational logs, while in-store data mainly consist of lower-frequency data such as purchased items and payment methods. Integrating these diverse datasets in a unified manner is difficult, and when trying to further account for combinations and sequences of customer interactions, the complexity and computational cost of analysis increase significantly.To address these challenges, NTT and DOCOMO jointly focused on solving them by selecting DOCOMO’s telemarketing operations as a use case for 1-to-1 marketing.Development Background and CollaborationDOCOMO has developed the “CX Analytics Platform,” which converts diverse customer touchpoint data into unified time-series data formatted according to the 4W1H format (Who, When, Where, What, and How). This platform has helped improve the efficiency of data utilization across marketing initiatives.Meanwhile, NTT has been conducting research and development on an AI technology called LAM, which learns and predicts patterns of behavioral sequences in time-series data that includes both numerical and categorical data (Figure 2). This technology has an architecture similar to large language models (LLMs) and enables future behavior prediction with a Transformer*3-based model.In this collaboration, the two companies integrated their respective technologies. By leveraging DOCOMO’s CX Analytics Platform to consolidate customer data into time-series form and applying NTT’s LAM with an optimized tuning method, they built DOCOMO’s proprietary LAM, achieving significant reductions in computational cost.Figure 2 LAMSummary of Results- Establishment and Optimization of the LAM TechnologyWhen dealing with large-scale models and data, improving prediction performance often comes at the cost of increased computational load. In this project, through careful design and parameter optimization, DOCOMO successfully built its proprietary LAM with a total computation cost of 145 GPU hours (132 GPU hours for pre-training and 13 GPU hours for additional training).During pre-training, parameters necessary for predicting customers’ intended actions were optimized. During additional training, parameters required for personalizing promotional activities were fine-tuned. The total computation time corresponds to less than one day on eight NVIDIA A100 (40GB) GPUs.For reference, this efficiency is approximately 1/568 of training Llama-1 7B, an open-source large language model that requires 82,432 GPU hours (see Figure 3). As a result, DOCOMO has accumulated expertise in building cost-effective LAM models and successfully applied this know-how to real-world marketing use cases.Figure 3 Comparison of construction costs between LAM and in-market LLM- Operational Improvements through 1-to-1 MarketingUsing DOCOMO’s proprietary LAM, customer needs and the necessity of telemarketing were quantified as scores. By prioritizing customers with higher necessity scores, the order rate for mobile and smart life-related services improved by up to 2 times compared to conventional methods (Figure 4).Interviews with several customers who received proposals revealed that the system enabled outreach at appropriate timings, such as to those who wished to complete procedures in-store but found it difficult to visit due to childcare, or to those who were undecided about changing their rate plans.Figure 4 Example application in the marketing sectorRoles of Each CompanyNTTResponsible for the research and development of LAM and the provision of tuning methods.DOCOMOResponsible for the research and development of the CX analytics platform, the training and inference of LAM using authorized personal information, and the provision of telemarketing services.Key Technical Features- CX Analytics PlatformAn analytics platform that supports service improvement by integrating a wide range of online and offline services and deepening customer understanding provided by DOCOMO. By organizing data in the 4W1H format (Who, When, Where, What, and How), it enables unified handling of data collected from diverse customer touchpoints.- LAMA Transformer-based time series prediction AI developed by NTT (Figure 2). It can handle mixed numerical and categorical data, including those with missing or biased values.The model captures differences in meaning based on the order of customer actions. For example, consider three actions: telemarketing, product page browsing, and purchase (Figure 5).If a customer receives a telemarketing call, then views a product page, and finally makes a purchase, telemarketing can be interpreted as promoting product awareness.If the sequence is browsing followed by telemarketing and then purchase, telemarketing is likely to have deepened the customer’s interest in the product.In contrast, if telemarketing occurs after purchase, it may indicate after-sales support for a potential issue.By distinguishing these contextual differences, the model enhances customer understanding and accurately predicts each customer’s intent.Furthermore, the model improves learning efficiency through innovations such as a hierarchical Transformer structure that progressively aggregates data with different frequencies and formats.Figure 5 Examples showing how the meaning of actions differs depending on their orderApplications of the LAM TechnologyNTT is exploring the potential applications of LAM technology across a wide range of fields. The know-how gained in building cost-effective LAM models is expected to be leveraged in other domains as well.* HealthcareIn the medical field, patients’ treatment histories are recorded as time-series data in electronic medical records. The order of disease progression and medication prescriptions carries important clinical meaning, and analyzing these patterns can provide valuable insights for treatment support. To this end, NTT is applying LAM technology to support diabetes treatment (Figure 6) *4.Figure 6 Example application in the health sector* Energy SectorSatellite and ground-based observations of meteorological phenomena are also recorded as time-series data. Solar power operators use these time-series data to forecast future solar radiation, develop generation plans, and conduct electricity trading with retail power suppliers. Fluctuations in the power output of geographically adjacent solar power facilities reflect the effects of cloud movement and position on solar radiation. Analyzing these patterns is useful for improving the accuracy of solar radiation forecasts. Therefore, NTT is also working on applying LAM to solar radiation forecasting (Figure 7).Figure 7 Example application in the energy sectorFuture DevelopmentsTo address real-world challenges through data-driven approaches, NTT will continue to enhance LAM technology. By 2028, we aim to improve the flexibility of data input and output for LAM, enabling it to handle most types of nonverbal data used in our business operations.DOCOMO will continue striving to offer personalized proposals for each individual customer.Related InformationIntroduction video of LAM: https://youtu.be/71nAVN0pvPg(*1) Personal data are handled appropriately in accordance with our privacy policy.(*2) NTT R&D FORUM 2025 IOWN ∴Quantum Leap official website:https://www.rd.ntt/e/forum/2025/(*3) A Transformer is a type of neural network architecture that converts an input sequence into an output sequence.(*4) Kurasawa H, et al. Enhancing Antidiabetic Drug Selection Using Transformers: Machine-Learning Model Development. JMIR Med Inform. 2025 Jun 2;13:e67748. doi: 10.2196/67748. PMID: 40456113; PMCID: PMC12148250.About NTTNTT contributes to a sustainable society through the power of innovation. We are a leading global technology company providing services to consumers and businesses as a mobile operator, infrastructure, networks, applications, and consulting provider. Our offerings include digital business consulting, managed application services, workplace and cloud solutions, data center and edge computing, all supported by our deep global industry expertise. We are over $90B in revenue and 340,000 employees, with $3B in annual R&D investments. Our operations span across 80+ countries and regions, allowing us to serve clients in over 190 of them. We serve over 75% of Fortune Global 100 companies, thousands of other enterprise and government clients and millions of consumers.About NTT DOCOMONTT DOCOMO, Japan's leading mobile operator with over 91 million subscribers, is one of the global leaders in 3G, 4G and 5G mobile network technologies. Under the slogan “Bridging Worlds for Wonder & Happiness,” DOCOMO is actively collaborating with global partners to expand its business scope from mobile services to comprehensive solutions, aiming to deliver unsurpassed value and drive innovation in technology and communications, ultimately to support positive change and advancement in global society. https://www.docomo.ne.jp/english/ Copyright 2025 JCN Newswire via SeaPRwire.com. All rights reserved. www.jcnnewswire.com

Cogeneration Facility at Miaoli Factory (Photo: Chang Chun Petrochemical) TOKYO, Nov 12, 2025 - (JCN Newswire via SeaPRwire.com) - Mitsubishi Power, a power solutions brand of Mitsubishi Heavy Industries, Ltd. (MHI), has received an order for an H-25 gas turbine for Chang Chun Petrochemical Co., Ltd. through Mitsubishi Corporation Machinery, Inc.Chang Chun Petrochemical is advancing plans to convert the cogeneration facility at its Miaoli Factory, located in Miaoli City in north-central Taiwan, from existing heavy oil and coal-fired boilers to a high-efficiency natural gas-fired system. The H-25 gas turbine will serve as the core of the new gas-fired cogeneration facility, with an output of approximately 30 MW. Operation is scheduled to begin around the end of 2028, supplying electric power and steam for manufacturing processes at the factory. Mitsubishi Power will deliver the main gas turbine and auxiliary equipment, as well as dispatch engineers to support equipment installation and commissioning.Mitsubishi Power previously received an order for an H-25 gas turbine for the Miaoli Factory in 2023, with operation planned to start around summer 2026. This order marks the second H-25 gas turbine to be installed at the same factory. Through improved plant efficiency and reduced CO2 emissions, this project will contribute to the realization of Taiwan's energy policy objectives.Chang Chun Petrochemical is a core company of Chang Chun Group, a major petrochemical conglomerate in Taiwan. Headquartered in Taipei, Chang Chun Group comprises numerous group companies and factories in Taiwan and around the world.Since 1984, Mitsubishi Power has supplied major equipment to power generation and cogeneration facilities at Chang Chun Group factories, including nine steam turbines and five boilers. Mitsubishi Power continues to provide after-sales services and various solution offerings. This latest order reflects the strong trust earned through this track record and the long-standing positive relationship between the two companies.The H-25 gas turbine has demonstrated high reliability supported by extensive long-term operational experience. Since receiving the initial order for the H-25 in 1987, Mitsubishi Power has delivered and operated more than 200 units worldwide. Utilizing the H-25 in cogeneration facilities enables improved plant efficiency and reduced CO2 emissions compared to conventional boiler-based systems that burn fuel directly.Mitsubishi Power will continue to actively expand its business in the distributed power generation market, including industrial private power generation and cogeneration systems worldwide, contributing to the strengthening of industrial infrastructure and the reduction of energy-related environmental impacts globally.About MHI GroupMitsubishi Heavy Industries (MHI) Group is one of the world’s leading industrial groups, spanning energy, smart infrastructure, industrial machinery, aerospace and defense. MHI Group combines cutting-edge technology with deep experience to deliver innovative, integrated solutions that help to realize a carbon neutral world, improve the quality of life and ensure a safer world. For more information, please visit www.mhi.com or follow our insights and stories on spectra.mhi.com Copyright 2025 JCN Newswire via SeaPRwire.com. All rights reserved. www.jcnnewswire.com

TOKYO, Nov 11, 2025 - (JCN Newswire via SeaPRwire.com) - Mitsubishi Motors Corporation (hereafter, Mitsubishi Motors) announced that its all-new kei-cars1, the Delica Mini and eK Space, have been jointly awarded the RJC Car of the Year award for 2026, run by the Automotive Researchers’ and Journalists’ Conference of Japan (RJC), alongside the Nissan Roox.Additionally, Mitsubishi Motors rally driver Hiroshi Masuoka has been honored with the RJC Person of the Year award for 2026. This prestigious accolade recognizes outstanding individuals in the automotive industry.  All-New eK Space and Delica Mini  Hiroshi MasuokaVice President, Mitsubishi Motors RJC Car of the Year AwardThis marks Mitsubishi Motors’ fifth win of the RJC Car of the Year award and the first in three years since the eK X EV (pronounced "eK 'cross' EV"), an all-electric kei-car, won the award2 for 2023.The Delica Mini is a super height-wagon kei-car that bears the name of the Delica minivan, which combines a spacious interior with powerful driving performance. The all-new model builds on the concept of its predecessor while making bold advancements in exterior and interior design, driving performance, safety features, ease of handling, and user-friendliness, making it ideal for both everyday driving and outdoor adventures.The all-new eK Space combines excellent maneuverability for city driving with a modern design that appeals to all generations, along with a spacious interior.* Comments from the Jury:While further enhancing the visibility and convenience expected of super height-wagon kei-cars, the models achieve both excellent fuel efficiency and refined driving performance. By incorporating unique elements into the interior and exterior designs to create three distinctive models – each built on a single platform developed by NMKV Co., Ltd., a joint venture between Nissan Motor Co., Ltd. and Mitsubishi Motors – the achievement demonstrates exceptional ingenuity and deserves significant praise.RJC Person of the Year AwardHiroshi Masuoka has competed in the Dakar Rally 21 times with Mitsubishi vehicles including the Pajero, achieving consecutive victories in 2002 and 2003, the first ever by a Japanese driver. From 2012 to 2014, he participated in the Pikes Peak International Hill Climb, and in 2015 in the Baja Portalegre, driving electrified vehicles as both a driver and team director.By participating in motorsports with competition vehicles based on mass-production models, as well as those incorporating both production components and advanced technologies, he has leveraged the expertise gained to enhance commercial vehicles, contributing to the advancement of high-performance electrified vehicles that support carbon neutrality. Additionally, his proactive involvement in social contribution activities to promote safe driving, including participation in Mitsubishi Motors’ SUV 4WD test drive events, was highly praised, leading to his recognition with the award.Currently, Masuoka serves as team director of Team Mitsubishi Ralliart, leading the team to overall victories in the Asia Cross Country Rally in 2022 and 2025.* Comments from the Jury:Masuoka achieved the first-ever consecutive wins by a Japanese driver in the Dakar Rally, and as a team director, led his team to two victories in the Asia Cross Country Rally. By competing with electrified vehicles, he has contributed to the development of electrification technologies that promote environmental sustainability. His role as a demonstration driver in the 4WD hill climb kit experience event, along with his active efforts to promote safe driving, was also highly commended.* Comment from Hiroshi Masuoka:“From a young age, I was fascinated by cars and spent countless hours honing my skills. I debuted in off-road racing at 18 and joined Ralliart at 22. Over the years, I have had the honor of competing in the Dakar Rally – the world’s most grueling rally – 21 times with Mitsubishi Motors, achieving long-awaited overall victories in both 2002 and 2003. I am deeply grateful to Mitsubishi Motors customers, Team Mitsubishi Ralliart fans, all those involved, and my family, who has supported me throughout my journey of over 40 years as a driver and team director. I will continue to contribute to the development of safe, reassuring, and comfortable vehicles by applying the experience gained through motorsports.”About the RJC Car of the Year for 2026Now in its 35th year, the RJC Car of the Year award is determined by votes from RJC’s selection committee. Eligible vehicles are domestic models premiered in the Japanese market between November 1, 2024, and October 31, 2025. The top six models were selected on October 31, with final voting held on November 11.Mitsubishi Motors has previously won the RJC Car of the Year award four times3, the RJC Technology of the Year award six times4, and the Special Award twice5.1. Kei-car is a vehicle category in Japan for microcars.2. Joint award with the Nissan Sakura3. Previous winners include the "i" kei-car (award for 2007); the Eclipse Cross, a crossover SUV (award for 2019); the eK Wagon and eK X, height wagon kei-cars (award for 2020) and the eK X EV, an all-electric kei-car (award for 2023).4. Previously recognized technologies include the INVECS (Intelligent & Innovative Vehicle Electronic Control System) automatic transmission technology used in the Galant and Eterna (award for 1993); the INVECS-II Sport Mode automatic transmission of the FTO (award for 1995); the GDI (Gasoline Direct Injection) engine of the Galant and Legnum (award for 1997); the PHEV system of the Outlander PHEV (award for 2014); the evolved PHEV and S-AWC systems of the Eclipse Cross (award for 2022); and the electrification technology of the all-electric kei-car used in the eK X EV (award for 2023).5. Previous winners include the Lancer Evolution X (award for 2009) and the Triton (award for 2025).About Mitsubishi MotorsMitsubishi Motors Corporation (TSE:7211) — a member of the Alliance with Renault and Nissan — is a global automobile company based in Tokyo, Japan, which has about 28,000 employees and a global footprint with production facilities in Japan and the ASEAN region. Mitsubishi Motors has a competitive edge in SUVs, pickup trucks and plug-in hybrid electric vehicles, and appeals to ambitious drivers willing to challenge convention and embrace innovation. Since the production of our first vehicle more than a century ago, Mitsubishi Motors has been a leader in electrification — launched the i-MiEV, the world’s first mass-produced electric vehicle in 2009, followed by the Outlander PHEV, the world’s first plug-in hybrid electric SUV in 2013. With a target of increasing the sales ratio of electrified vehicles to 100% by 2035, Mitsubishi Motors will deliver models that embody Mitsubishi Motors-ness and contribute to the realization of a carbon-neutral society. For more information on Mitsubishi Motors, please visit the company's website at https://www.mitsubishi-motors.com/en/  Copyright 2025 JCN Newswire via SeaPRwire.com. All rights reserved. www.jcnnewswire.com

TOKYO, Nov 12, 2025 - (JCN Newswire via SeaPRwire.com) - TANAKA PRECIOUS METAL TECHNOLOGIES Co., Ltd., an industrial precious metals organization, has announced the development of TK-SR, a rhodium (Rh) material for probe pins used in probe cards during the front-end processes of semiconductor package manufacturing. This first of its kind product will be exhibited on display at Booth 506 and panel displays at SWTest Asia 2025 from November 20 to November 21 in Fukuoka, Japan. "TK-SR" product image Comparison of stress-strain curve for probe Rh and conventional TANAKA RhTANAKA manufactures and supplies various precious metal probe pin materials for the inspection equipment used in the front- and back-end processes of semiconductor manufacturing. Using its proprietary processing technologies, TANAKA is the first company in the world to successfully develop a rhodium probe pin material that simultaneously offers high strength, elasticity, hardness, and electrical conductivity that will extend the lifespans of probe cards and lower their costs.TK-SR is available in widths as narrow as 18μm, enabling precision inspection for today’s increasingly compact narrow-pitch semiconductor packages. TANAKA plans to ship twice as many of these products as conventional products by 2030.Probe cards play a critical role in current-carrying tests on silicon wafers during front-end semiconductor processes, using thousands or sometimes tens of thousands of precision probe pins. These pins endure extremely light loads applied hundreds of thousands, or even millions, of times. If a single probe pin bends or breaks, it must be replaced, and in some cases, the entire probe card. That’s why durability is essential. TANAKA’s high-strength, high-elastic limit TK-SR significantly reduces the risk of deformation and breakage, minimizing replacement frequency and improving overall reliability.TK-SR Product Performance (reference values)Comparison of TK-SR and Convention Rh Wire PropertiesExhibition Details- Exhibition Name: SWTest Asia 2025- Dates and Times: November 20 to November 21, 2025, 8:00 a.m. to 5:00 p.m.- Location: Hilton Fukuoka Sea Hawk (Fukuoka, Japan)- Website: https://www.swtestasia.org/- Exhibitor: TANAKA PRECIOUS METAL TECHNOLOGIES Co., Ltd.- Booth No.: 506- Panel Contents: TK-SR (wire) rhodium material for probe pins, TK-FS (wire, plate), TK-SK (wire), palladium alloy material for probe pins, TK-101 (plate) copper and silver alloy material for probe pins, and plating solution for probe pins (various types)To learn more about TANAKA’s probe pin offerings and contributions to the semiconductor market, visit: https://tanaka-preciousmetals.com/en/products/detail/probe-pins/  About TANAKASince its foundation in 1885, TANAKA has built a portfolio of products to support a diversified range of business uses focused on precious metals. TANAKA is a leader in Japan regarding the volume of precious metals it handles. Over many years, TANAKA has manufactured and sold precious metal products for industry and provided precious metals in such forms as jewelry and assets. As precious metals specialists, all Group companies in Japan and worldwide collaborate on manufacturing, sales, and technology development to offer a full range of products and services. With 5,591 employees, the group’s consolidated net sales for the fiscal year ended December 2024 were 846.9 billion yen.TANAKA Industrial Precious Metal Materials Portalhttps://tanaka-preciousmetals.comProduct inquiriesTANAKA PRECIOUS METAL TECHNOLOGIES Co., Ltd.https://tanaka-preciousmetals.com/en/inquiries-on-industrial-products/Press inquiriesTANAKA PRECIOUS METAL GROUP Co., Ltd.https://tanaka-preciousmetals.com/en/inquiries-for-media/Press Release: https://www.acnnewswire.com/docs/files/20251112_EN.pdf  Copyright 2025 JCN Newswire via SeaPRwire.com. All rights reserved. www.jcnnewswire.com