Training Outcomes Research Articles

The effectiveness of corporate diversity training from the trainers' perspective: results of a qualitative study in Germany

PurposeOrganizational diversity training is designed to enhance employees' skills and competencies regarding diversity and its management. The question of its effectiveness, and the conditions under which it thrives, remains a matter of debate. Unlike previous studies that have predominantly focused on the perspective of training participants, this study shifts the lens to the viewpoints of diversity training providers in Germany – a country where the formal requirement for diversity management was implemented relatively recently. The primary objective is to ascertain the critical factors influencing training effectiveness from the providers' perspective.Design/methodology/approachThis research draws upon case studies based on document analysis and qualitative interviews with diversity training providers across Germany.FindingsThe investigation reveals that the effectiveness of diversity training, as perceived by providers, hinges on several key factors: the organizational environment (including the widespread recognition of diversity issues and the presence of an organizational diversity framework), the attributes of diversity trainers (notably their personal familiarity with diversity) and the setting and design of the training (such as venue, duration and a blend of instructional approaches). A notable barrier to achieving effective training outcomes is the lack of supportive conditions within client companies, exemplified by limited training budgets, which impedes the accurate assessment of training effectiveness.Originality/valueThis study marks a novel contribution to the field by explicitly focusing on the perspective of diversity training providers in Germany. It provides new insights into the importance of the organizational context surrounding diversity education within the private sector.

Preliminary Evidence for a Teacher Training Model on Social/Emotional/Behavioral Universal Screening in Schools

ABSTRACT This preliminary study was designed to evaluate the outcomes of iterative teacher trainings for social/emotional/behavioral (SEB) screening in schools. Three separate and successive trainings were completed with adjustments made based on the previous training. We examined the level of accuracy in SEB screener knowledge and data-based decision-making (DBDM) teachers had after training. Additionally, we examined assessment items for patterns in performance on SEB screener knowledge and DBDM after training. Training 1 included 18 preservice teachers, who had greater than chance-level performance on screener knowledge and DBDM at posttest. Training 2 included 16 preservice teachers and Training 3 included 36 in-service teachers. Changes in pre- to posttest performance from these trainings indicated that there was an increase in screener knowledge and DBDM with large effect sizes. An examination of SEB knowledge and DBDM items indicated regular areas of strengths and deficits for the teacher after receiving the training. Implications for adjusting the training procedures and delivery, and examining teacher needs related to SEB screening knowledge and DBDM are discussed.

Enhancing Multiple Object Analysis Skills Across Early and Late Adulthood Through Diverse Tasks

Tasks on multiple targets involve, to some extent, at least two capacity-limited classes of mechanisms: attentional individuation and visuo-spatial working memory (vWM). It is also known that these mechanisms tend to decline with aging. In this study, we hypothesized that if both mechanisms underlie the analysis of multiple objects, then training one task involving multiple objects should benefit other tasks requiring multiple object processing, regardless of task contents or instructions. In addition, we predicted that older adults would benefit more from the training protocol. To test these hypotheses, we trained two groups of young and older participants, one with a delayed match-to-sample (DMTS) task and one with rapid enumeration. Training effects (compared to test/re-test effects of a passive control group) were assessed on both DMTS and rapid enumeration. Results indicated a training-related benefit within and across tasks, regardless of age. Older adults’ gain from training was larger compared to the young counterpart. In addition, and irrespective of age, individual differences in baseline performance correlate with training outcomes, with compensatory activity likely occurring for low-performing individuals.

GAN-based self-supervised message passing graph representation learning

Graph representation learning aims to learn embedding representations of nodes in graph-structured data through supervised or unsupervised methods. However, for unlabeled or sparsely labeled graph datasets, conventional supervised approaches fail to perform adequately, and existing unsupervised methods have difficulty achieving high accuracy on multiple downstream tasks such as node classification and link prediction at lower embedding dimensions. To address this issue, we propose a novel self-supervised graph representation learning approach called GAN-based Message Passing Graph Representation Learning. This approach significantly improves the accuracy of node embeddings without relying on label information. Specifically, GMP-GL has developed a generator based on neighbor-weighted random walk to obtain positive and negative node sample pairs, as well as a discriminator that distinguishes whether a real connection exists between node pairs. Through adversarial learning, GMP-GL automatically learns node embeddings. Furthermore, GMP-GL optimizes the training outcomes of the generative adversarial model through self-supervised embedding aggregation learning, thus introducing rich structural information from the graph for the subsequent rounds of generative adversarial training. In addition, GMP-GL employs multiple autoencoders to generate and filter original embeddings, ensuring that the pre-embeddings preserve a significant amount of original feature information for formal learning. The study selects six real-world datasets and conducts comparative experiments with ten SOTA baseline methods. The experimental results demonstrate that the proposed model not only surpasses previous unsupervised methods but also matches or even exceeds the performance of supervised methods. This indicates the great potential of the proposed approach for representation learning tasks on unlabeled graph datasets and its effective applicability to real-world problems.

A pilot study evaluating online training for therapist delivery of interpersonal psychotherapy for eating disorders.

Individuals with eating disorders (EDs) often do not receive evidence-based care, such as interpersonal psychotherapy (IPT), partly due to lack of accessible training in these treatments. The standard method of training (i.e., in-person workshops) is expensive and time consuming, prompting a need for more scalable training tools. The primary aim of this pilot and open trial was to examine the effects of an IPT online training platform on training outcomes (i.e., IPT fidelity, knowledge, and acceptance) and, secondarily, whether online training was different from in-person training (using a comparative sample from a separate study) in terms of training outcomes and patient symptoms. Participants were therapists (N = 60) and student patients (N = 42) at 38 college counseling centers. Therapists completed baseline questionnaires and collected data from a student patient with ED symptoms. Therapists then participated in an IPT online training program and completed post-training assessments. Following online training, acceptance of evidence-based treatments, therapist knowledge of IPT, therapist acceptance of IPT, and treatment fidelity increased; acceptance of online training was high at baseline and remained stable after training. Using the 90% confidence interval on outcome effect sizes, results suggested IPT online training was not different from in-person training on most outcomes. Results are based on 60% of therapists who originally enrolled due to high dropout rate of therapist participants. Findings from this preliminary pilot study support the use of IPT online training, which could increase access to evidence-based ED treatment and improve patient care. Lack of accessible therapist training has contributed to many therapists not delivering, and therefore many patients not receiving, evidence-based treatment. This study evaluated a highly disseminable online training and compared outcomes to traditional in-person training and found that training and patient outcomes were not different. Online training has the potential to enhance access to evidence-base care, which could in turn optimize patient outcomes.

Conditioned overconsumption is dependent on reinforcer type in lean, but not obese, mice.

Associative learning can drive many different types of behaviors, including food consumption. Previous studies have shown that cues paired with food delivery while mice are hungry will lead to increased consumption in the presence of those cues at later times. We previously showed that overconsumption can be driven in male mice by contextual cues, using chow pellets. Here we extended our findings by examining other parameters that may influence the outcome of context-conditioned overconsumption training. We found that the task worked equally well in males and females, and that palatable substances such as high-fat diet and Ensure chocolate milkshake supported learning and induced overconsumption. Surprisingly, mice did not overconsume when sucrose was used as the reinforcer during training, suggesting that nutritional content is a critical factor. Interestingly, we also observed that diet-induced obese mice did not learn the task. Overall, we find that context-conditioned overconsumption can be studied in lean male and female mice, and with multiple reinforcer types.

Improved Quantum Approximate Optimization Algorithm for Low‐Density Parity‐Check Channel Decoding

AbstractQuantum computing shows promise for 6G networks due to its parallel computing capabilities. In the context of the Noisy Intermediate‐Scale Quantum era, the introduction of hybrid quantum‐classical algorithms like Quantum Approximate Optimization Algorithm (QAOA) offer powerful solutions to many combinatorial optimization problems in 6G. This paper focuses on Low‐Density Parity‐Check (LDPC) channel decoding and proposes an improved QAOA algorithm assisted by the learning‐to‐learn strategy. We also investigate the parameter concentration phenomenon in QAOA‐based LDPC decoding to assess the rationality. To evaluate effectiveness, a comprehensive numerical expression for the energy expectation of single‐layer QAOA and propose indicators for transfer performance evaluation is provided. Based on simulation results, the similarity in parameter distribution across specific LDPC configurations is investigated. This similarity facilitates the transfer of training outcomes from smaller to larger‐scale problems for optimization initialization, thereby avoiding the need for retraining. This approach offers insights and potential solutions for rapid, large‐scale channel decoding in 6G networks, despite the current limitations of quantum hardware.

A novel facial age estimation through super-resolution based on deep learning

Age estimation encounters challenges due to the low resolution (LR) of images captured in real-world scenarios, emphasizing the critical role of image quality in achieving accurate age estimations. Despite efforts to enhance age estimation through LR image training, existing methodologies often overlook the incorporation of super-resolution (SR) as a crucial pre-processing step for LR images. This study introduces an innovative approach that integrates SR of facial images with age estimation methodologies. Specifically, a hierarchical reconstruction network (HRN) structure is employed to train LR images, fully integrating shallow concrete features and deep abstract features. Validation of the training outcomes includes evaluation metrics such as peak signal-to-noise ratio and structural similarity index measurement, showing superior performance compared to several state-of-the-art approaches. Subsequently, an enhanced soft stage regression network is designed for facial age measurement and trained using the SR-IMDB dataset generated by HRN to minimize mean absolute error. This approach achieves a final result of 7.33, indicating an average performance improvement of 10.94% compared to five other state-of-the-art methods. Experimental results highlight the effectiveness of integrating SR into the age estimation process.

Online versus in-person gatekeeper suicide prevention training: comparison in a community sample

Background Suicide prevention gatekeeper Training (GKT) is a frequently used suicide prevention intervention, however, there is still limited information about its long-term impact and effectiveness of online delivery. Aims The current study aimed to test the effectiveness of online GKT compared to in-person GKT in improving participant training outcomes. Methods A non-randomised comparison of pre-, post- and six-month follow-up data was conducted. In total 545 people participated in GKT, 317 in SafeTALK in-person sessions and 228 in online “Start” GKT by LivingWorks. Main outcome measures included: perceived knowledge; perceived preparedness; gatekeeper efficacy; and gatekeeper reluctance to intervene. Results Linear mixed model analysis demonstrated a significant effect for time for both modes of delivery for all four outcome measures. Post-hoc testing revealed that significant improvement in all outcomes were maintained above baseline at six-months following online and in-person training. Conclusions Online training performed as good, or better than in-person GKT, on measured outcomes demonstrating utility and effectiveness of the modality for use in suicide prevention training practices. Findings additionally indicate that online training may reach participants that in-person programs do not. This study provides evidence that Online GKT has significant utility in addressing a crucial need for online alternatives to evidence-based suicide prevention training.

Novel Cost-Effective Model for Training Post-intubation Endotracheal Tube Placement Confirmation.

Intubation in emergency settings demands rapid confirmation of endotracheal tube (ETT) placement for establishing a definitive airway. Current methods, including capnography and auscultation, have limitations. This study introduces a cost-effective and easily accessible training model for confirming ETT placement using ultrasound, aiming to improve training and patient outcomes. We developed a gelatin and psyllium-based model that simulates adult ETT intubation, offering an alternative to costly cadaveric models. The model's construction is described, with materials costing approximately $7.34 per unit. Preliminary results show promise in simulating tracheal and esophageal intubation scenarios. This novel model provides an ethical and economical solution for training healthcare professionals in the ultrasound confirmation of ETT placement, paving the way for further validation and adoption in medical education.

Efficacy of ScopeGuide-Assisted Training in Enhancing Colonoscopy Competence and Reducing Patient Discomfort.

In this study, we aimed to evaluate the efficacy of the Magnetic Scope Guide Assist (ScopeGuide) in enhancing the procedural competence of endoscopists and reducing patient discomfort during colonoscopy. This was a retrospective study with 88 trainee participants. The study participants were trained on patients who underwent colonoscopy without anesthesia. Both ScopeGuide-assisted training and conventional training (without ScopeGuide) were utilized for colonoscopy instruction. The outcomes of training were compared, with a particular emphasis on the competency of looping resolution. ScopeGuide-assisted training was superior to conventional training in multiple aspects, including looping resolution ( Z =-3.681, P <0.001), pain scores ( Z =-4.211, P <0.001), time to reach the cecum ( Z =-4.06, P <0.001), willingness to undergo repeat colonoscopy ( Z =-4.748, P <0.001), competence of positional changes ( Z =-4.079, P <0.001), and the effectiveness of assisted compression ( Z =-3.001, P =0.003). Further stratified analysis revealed that the ScopeGuide-assisted training mode was more beneficial for junior endoscopists ( P <0.05 in all parameters) but not for intermediate endoscopists ( P >0.05) and partially beneficial for senior endoscopists ( P <0.05 for all parameters except looping resolution). ScopeGuide-assisted training can significantly facilitate endoscopists in resolving loops and reducing patient pain, thereby enhancing their colonoscopy abilities.

Psychiatry resident physician duty hours, resting times and European Working Time Directive compliance in Spain

Introduction There is a growing interest in understanding the impact of duty hours and resting times on training outcomes and the well-being of resident physicians. Psychiatry resident’s duty hours in Spain comprise a regular working schedule of 37.5h per week and a minimum of 4 mandatory on-call shifts. The most recent duty hours regulations in Spain were transposed from the European Working Time Directive (EWTD). According to Spanish Law, doctors cannot work for more than 48h per week and need to have resting times per day (at least 12h), per week (at least 36h) as well as annual leave (at least a month). However, there is practically no data on this situation in psychiatry resident physicians.Objectives Our aim is firstly, to describe the number of shifts performed by psychiatry resident physicians in Spain. Secondly, to describe compliance with the daily and weekly rests compared to those set in national and European law. Finally, to analyse the difference by demographic variables (gender and year of residency), in both the number of on-call duty shifts and compliance with rests.MethodsA descriptive cross-sectional study was designed through an online survey adapted from the existing literature. The target population were Spanish psychiatry resident physicians undergoing PGT who started their specialist training during the years 2018–2021. The survey was disseminated through the Spanish regional medical councils to all active psychiatry resident physicians by mail as well as through informal communication channels. The study was authorised by the Spanish Medical Organization’s General Assembly which is the highest ethical and deontological body of physicians in Spain.Results 55 responses were obtained, of which 61.82% identified as females. The mean number of on-call shifts in the last 3 months was 14.05. This mean was highest in women 14,32 and in the cohort of 2020 15.46 (first year of residency). Among the resident physicians surveyed, 66.07% exceeded the 48h per week limit set by the EWTD and 7% of them did not rest after a 24-h on-call shift. Furthermore, 22% of respondents did not have a day-off after a Saturday on-call shift. The mean working hours when not resting after an on-call-shift were 7 hours. The comparison by gender and year of residency of the main variables can be seen in figures 1 and 2 respectively.Image:Image 2:ConclusionsPsychiatry resident physicians in Spain greatly exceed the established 48 h/week EWTD limit. Likewise, non-compliance with labour regulations regarding mandatory rest after on-call duty and minimum weekly rest periods are observed. Differences can be seen by gender and year of residency. The situation described could potentially create a high-risk situation for the health and psychosocial well-being of resident physicians, hinder learning outcomes and could lead to suboptimal patient care.Disclosure of InterestNone Declared

165 Predicting Success: A Mixed Model of KL2 Trainee Profiles and Outcomes

OBJECTIVES/GOALS: Penn State CTSI supports KL2 career development awards for faculty seeking to become leaders in clinical and translational research. CTSAs can benefit from a better understanding of KL2 applicant profiles and trainee outcomes. Predictive modeling of KL2 records provides insights into institutional processes and continuous improvement goals. METHODS/STUDY POPULATION: Collecting KL2 application records at Penn State CTSI from 2017 to 2023, comprising both accepted and not accepted candidate profiles, this study used a generalized logistic mixed model with binomial distribution to understand the factors predictive of KL2 trainee acceptance, (n=47). The following factors were modeled as potentially predictive of scholars’ acceptance: Institution-specific Processes—Campus; Terminal Degree Type; College of Residency, Applicant Demographics and Portfolio—Minoritized or Protected Groups; Mean Application Score; Rurality Focus; Gender, and Outcomes—Post-Program h-index. RESULTS/ANTICIPATED RESULTS: Only Campus and Degree were significant factors predictive of trainee acceptance (r&lt;.0001), with a particular campus and the MD degree-designation both exerting selectional pressures on acceptance rates. Applicant demographics were not significant historical factors in selection despite the most recent trainee cohort comprised of all women. Similarly, while our CTSA focuses on rural inequality and accessibility, a research proposal focused on rurality was not a significant factor for acceptance. Notably, NIH-scaled application scores and post-program h-indices were not significant for accepted and non-accepted applicants. DISCUSSION/SIGNIFICANCE: The absence of applicant-focused selectional pressure is striking—Penn State CTSI does not significantly select for gender, URM, or URP status. Administration is now empowered to intentionally engage, recruit, and retain from our other affiliated campuses and colleges.

143 Training &amp; Sustaining: Training and learning collaborative outcomes across a statewide network for early diagnosis of children with autism

OBJECTIVES/GOALS: Community-based primary care autism diagnostic models are one promising solution to delays in autism diagnosis. Our objective is to describe the development and report on outcomes related to primary care professional (PCP) training and sustained engagement in a longitudinal learning collaborative across a statewide network for autism diagnosis. METHODS/STUDY POPULATION: We developed ADAPT (i.e., Accelerating the Diagnosis of Autism with Primary care Training), a training program to prepare PCPs to develop independent competency in evaluation of autism in children ages 14-48 months. ADAPT includes didactic and case-based modules and expert practice-based coaching delivered by a diagnostic specialist; following training PCPs participate in a longitudinal learning collaborative. Aligned with competency-based medical education standards, measures of autism evaluation knowledge and diagnostic competency are collected. RESULTS/ANTICIPATED RESULTS: To date, 13 PCPs have completed ADAPT didactic and practicum training reaching competency in independent autism evaluation. Clinicians demonstrated significant improvement in total autism knowledge following didactic training (p=.02). There was an overall trend toward increased scoring agreement on an autism observational assessment over case observations and practicum evaluations. Similarly, PCPs demonstrated improved evaluation competence, moving on average from Advanced Beginner to Competent Performer as rated by expert trainers. Following training, PCPs attended 57% of monthly learning collaborative sessions. DISCUSSION/SIGNIFICANCE: Training PCPs to deliver autism evaluations as part of community-based models of care is a promising solution to address access and waitlist challenges. ADAPT is an intensive, standard PCP training model which results in achievement of independent competency and sustained engagement in in autism evaluation.

Advancements in Hypospadias Management: Trends, Techniques, Training, and Patient-Centric Outcomes.

Hypospadias has drawn increasing attention due to its prevalence, complex etiology, and significant impacts on psychological and sexual quality of life. This comprehensive review delves into the facets of hypospadias management, exploring pivotal themes that shape present understanding and practice. We demonstrate potential explanatory factors for its incidence through an analysis of geographic, genetic, and environmental influences. We then contextualize care by exploring historical and evolving surgical techniques, and highlight that advances in surgical approaches employ a spectrum of repair strategies. Innovation in surgical training, with a focus on simulation-based methodologies, offers a bridge between didactic learning and real-world application, which is particularly relevant due to the demonstrated effect of personal experience with hypospadias repair outcomes. Considering the importance of mentorship, case exposure, and hands-on practice, a holistic understanding of expertise cultivation at each training stage is essential. Lastly, patient-centric outcomes research must take center stage, particularly as the impact of our interventions on children with hypospadias will be judged by them as adults. Shifting from solely surgeon-reported outcomes to patient-reported outcomes is emphasized in the review, allowing for a more comprehensive assessment of the influence of surgical interventions across the lifespan. Integrating patients' perspectives refines surgical decision-making to align with expectations, ultimately enhancing overall satisfaction. Our multi-pronged exploration of advancements in hypospadias underscores the symbiotic relationship between evolving surgical techniques, training methodologies, personal experience, and patientreported outcomes. As the field progresses, these insights will collectively contribute to optimizing hypospadias care, advancing both medical practice and patient well-being.

Outcome of Plyometric Training on the Performance of Female Badminton Players of the Islamia University of Bahawalpur

This research determined the differences between two groups of female badminton players. The participants were an experimental (group = 20 and a control group =20). The variables were obtained speed, flexibility, agility, standing jump, sit-ups, push-ups, body mass, height, anthropometric measures, and forehand services. Captured videos of the badminton serves were analyzed to obtain the kinematics measure. The experimental group followed a 6-week plyometric training and the control group continued with the same pattern of badminton practice. Factorial ANOVA with repeated measures was applied for statistical analysis. Findings showed the experimental group players were considerably greater in post-measurements in calf circumference, toe-to-toe distance stance, toe-to-toe distance connect shuttle, right elbow angle, and badminton performances. Therefore, it is concluded that the experimental groups significantly improved in physical fitness and badminton performance. It is suggested that female badminton players should follow plyometric training to enhance their fitness and badminton performance.

Analytics of Personal Motivation on Acquiring Skills for Workforce with reference to skill development Programmes

Purpose: The research aims to inspect and estimate the impact of Personal motivation of trainees on Skill acquiring in skill training. It identifies the relationship between the personal input its impact on the training process and the relation it produces in the outcome (skills acquired)&#x0D; Design/methodology/approach: A questionnaire for the study was designed, and information was composed on a multistage random sampling basis. Three hundred and eighty-four samples of data were collected and analyzed using Smart PLS - Structural Equation Modeling (SEM) technique.&#x0D; Findings: The study shows that Personal motivation plays a positive role in the skill gain of rural youth. It is also clear from the model that training processes like quality and relevance play a mediating role in acquiring skills. The factors help in the understanding type of input to be concentrated by the policymakers to increase a specific outcome. All the factors influence the training outcome (skill acquired) positive results.&#x0D; Research limitations/implications: This study covers only personal motivation as trainee input. Other training inputs like social factors, economic factors, and equality factors may further be included in future studies.&#x0D; Social Implications: The study will help the policymakers to get focus on which area the rural youth must be motivated to get the desired outcome. In this case, personal motivation is the key for rural youth to gain skills. Also, the training institutes must ensure that they provide good quality and relevance to boost the personal behavior of rural youth. If a training institute aims at only adding skill gain to the rural youth the major factor to be boosted is the personal factor.&#x0D; Originality/Value: Only limited studies have examined the impact of Personal factors on the Skills acquired as training outcome with quality and relevance as mediating factors of Smart PLS is a novel idea, and it is a first-hand study of its kind.

Does Social and Organizational Support Moderate Emotional Intelligence Training Effectiveness?

Given the dearth of systematic research and inconclusive results regarding the effectiveness of emotional intelligence (EI) training in adult training, this study was conducted to evaluate the effectiveness of EI training. This study aimed to assess the effectiveness of EI training on learning and transfer outcomes, considering underexplored moderation of social and organizational support with experimental and longitudinal research design. Training transfer was measured through changes in organizational citizenship behavior (OCB) and counterproductive work behavior (CWB). Participants self-assessed their OCB and CWB levels, while their supervisors also provided evaluations, allowing for separate analysis. Data, from a sample comprising 176 government officials, were collected across different periods and analyzed employing diverse analytical tools. The results revealed positive effects of EI training on training outcomes in both samples but positive moderation effect of social and organizational support on the effect of EI training on training outcomes was observed in the self-evaluation sample but not in the supervisor evaluation sample. The findings advance the debate on social exchange theory and organizational support theory by showing the boundary condition of their applicability. Furthermore, this study clarifies the impact of EI training on training outcomes by emphasizing the nuanced role of social and organizational support.

Virtual reality-based bioreactor digital twin for operator training

The use of immersive technologies and digital twins can enhance training and learning outcomes in various domains. These technologies can reduce the cost and risk of training and improve the retention and transfer of knowledge by providing feedback in real-time. In this paper, a novel virtual reality (VR) based Bioreactor simulation is developed that covers the set-up and operation of the process. It allows the trainee operator to experience infrequent events, and reports on the effectiveness of their response. An embedded complex simulation of the bioreaction effectively replicates the impact of operator decisions to mimic the real-world experience. The need to train and assess the skills acquired aligns with the requirements of manufacturing in a validated environment, where proof of operator capability is a prerequisite. It has been deployed at UK’s National Horizons Center(NHC) to train the trainees in biosciences.

Stock prediction and analysis based on machine learning algorithms

The stock market has consistently remained a focal point of substantial concern for investors. Nevertheless, due to the intricate, tumultuous, and often noisy nature of the stock market, forecasting stock trends presents a formidable obstacle. To augment the accuracy of stock trend predictions, the author adopts a combination of the Long Short-Term Memory (LSTM) neural network and a noise reduction technique known as Ensemble Empirical Mode Decomposition (EEMD). This composite model is employed to develop predictions for the daily stock price increases, aiming to provide more precise insights into market behavior. The framework is capable of generating the daily stock price change trend curve based on the training outcomes. EEMD, standardization, and other data preprocessing methods can effectively reduce the noise of the stock market. In this paper, three U.S. stocks from 2010 to 2023 are chosen as the research subjects. After the training is completed, the prediction curve generated by the model closely aligns with the actual curve. Furthermore, three commonly used evaluation metrics were utilized to assess the models performance. Based on all those experimental outcomes, this model adeptly forecasts the stocks trend.