Platform Goals Research Articles

AI Based Tamil Palm Leaf Character Recognition

A brand-new character recognition method has been created especially for Tamil manuscripts written on palm leaves. A variety of preprocessing techniques are used to obtain reliable recognition because these manuscripts are complicated and have age-related deterioration. Using cutting-edge image processing techniques, manuscript photos are enhanced and preprocessed in the earliest stage to improve clarity. Then, in accordance with the distinctive arrangement of these historical artifacts, these photos are divided into three separate portions. After segmentation, these parts are converted to grayscale to create the ideal contrast needed for character detection. Noise canceling algorithms have been incorporated to prevent any distortions or degradations that may occur as a result of the age of the manuscripts or other environmental influences. After this mitigation, the photos are binarized to emphasize the isolation of the figures from their surroundings. This makes sure that each character stands out clearly, laying the groundwork for the crucial next step: segmenting individual characters. The foundation of the training phase is this segmentation. Convolutional neural networks (CNNs), which excel at handling image-based tasks, were incorporated into the deep learning architecture used for model building. Utilizing a sizable dataset compiled from numerous articles, the model underwent intensive training. As a result, the model was able to recognise characters from these texts with an astounding accuracy rate of 89%. With the help of Flask, the complete system has been easily integrated into a user-friendly web interface. This platform's goal is quite clear: fusing the elegance and profundity of ancient scripts with the effectiveness of contemporary technology. It is positioned as a crucial tool for both academic research and teaching purposes. By doing this, it guarantees that the priceless history and knowledge found in these manuscripts remain accessible and lays the groundwork for their preservation for future generations. Keywords— Character recognition, Tamil palm manuscripts, Preprocessing, Visual clarity, Grayscale conversion, Noise cancellation, Binarization, Segmentation, Training, Flask-based web interface, Research, Education.

Optimal contract design for live streaming platforms under dual asymmetric information considering corporate social responsibility

AbstractWhen live streamers sell products to consumers on live streaming platforms, their abilities and service efforts are private, and thus, the issues of identifying their true abilities, motivating them to use appropriate service efforts, and providing a mechanism to allocate profits remain to be resolved for live streaming platforms. Adopting a principal–agent model, we investigate the optimal contract design between a live streaming platform and live streamers. In addition, we study the impacts of the price and service competition between live streamers and the platform's corporate social responsibility on the optimal contract design. The results show that high commission rates and low signing bonuses are not always beneficial to platforms, and the optimal contract design to identify the types of live streamers can make it more profitable. In addition, the utility‐maximizing platform always sets lower commission rates and signing bonuses compared with the profit‐maximizing platform. Regardless of the platform's goal, total profits and commission rates are higher under competition compared with no competition. For the government, policies and subsidies should be provided, such as regulating commission rates by setting a limited range and increasing subsidies for the marginal costs of live streaming platforms, which can effectively motivate live streaming platforms to enhance corporate social responsibility.

Dynamic Learning in Large Matching Markets

We study a sequential matching problem faced by large centralized platforms where "jobs" must be matched to "workers" subject to uncertainty about worker skill proficiencies. Jobs arrive at discrete times (possibly in batches of stochastic size and composition) with "job-types" observable upon arrival. To capture the "choice overload" phenomenon, we posit an unlimited supply of workers where each worker is characterized by a vector of attributes (aka "worker-types") sampled from an underlying population-level distribution. The distribution as well as mean payoffs for possible workerjob type-pairs are unobservables and the platform's goal is to sequentially match incoming jobs to workers in a way that maximizes its cumulative payoffs over the planning horizon. We establish lower bounds on the regret of any matching algorithm in this setting and propose a novel rate-optimal learning algorithm that adapts to aforementioned primitives online. Our learning guarantees highlight a distinctive characteristic of the problem: achievable performance only has a second-order dependence on worker-type distributions; we believe this finding may be of interest more broadly.

A Dynamic Equilibrium Mechanism of Core Layer Interests in the Mobile Medical Platform Ecosystem.

In recent years, with the development of the mobile Internet, big data, and cloud computing, the mobile medical platforms such as Ding Xiang Yuan aggregating platform ecological resources have played an irreplaceable role in improving efficiency, optimizing resource allocation, and even promoting the transformation and upgrading of the medical industry. Despite all this, most mobile medical platforms in China still face many problems, including the immature business model, the stagnation of the interaction of knowledge and information among platform members, and the weak platform competitiveness. Based on a review of the platform and commercial ecosystems, this paper adopts the evolutionary game method and simulation to analyze the evolutionary stability strategy of operators, partners, and users in the core layer of the platform during preflow and postflow periods of a mobile medical platform, hence, to construct a beneficial dynamic equilibrium model of a platform business ecosystem under the optimal decisions made by all parties involved in the platform: the goal in the early stage (preflow period) is to increase platform user flow. Hence, the knowledge/information sharing of platform users is needed to enhance platform's visibility. While in the late period (postflow period), when the platform user flow reaches a certain scale, platform's goal is to promote revenue, which relies mainly on the pricing strategy. It is critical to promote the stability of the platform and the dynamic balance of interests at the core layer in the pricing process. This paper applies the platform business ecosystem theory and the evolutionary game theory to mobile medical platform development, contributing theoretically and practically in the following: (1) providing a more solid theoretical support for the mobile medical platform research and enriching the theoretical framework of the platform business ecosystem; (2) proposing the dynamic equilibrium model based on the optimal decisions of the platform core layers, which help to reveal the inherent law of the evolution of the mobile medical platform; (3) providing policy suggestions and management implications in constructing an appropriate business ecosystem and achieving sustainable development in mobile medical platforms.

Design of Platform Reputation Systems: Optimal Information Disclosure

Reputation systems play a central role in a variety of marketplaces to eliminate information asymmetry between sellers and buyers. Despite their crucial role, the design of reputation systems remains a complicated issue. Some platforms try to disclose as much product information as possible through their reputation systems, by encouraging consumers to leave reviews or ratings. In contrast, some platforms disclose only partial product information to the public. Platforms, as the designers of such reputation systems, are thus an additional player added to conventional seller-buyer games. This paper studies the optimal information disclosure in a reputation system from the platform's profit standpoint. In a three-player game, sellers with different base quality decide investment in quality, the platform decides the amount of information about the product quality (i.e., ratings) to disclose through its reputation system, and the future consumer as the receiver makes the purchase decision after observing the information about the product quality. By modeling consumers as Bayesian learners, we specify conditions under which withholding some private information of the sellers can serve the platform's goal of maximizing profits by incentivizing seller investment in quality. We find that, although fully disclosing information can eliminate information asymmetry, it may hinder the sellers' incentive to invest in quality, which hurts the platform's profits. Two main effects are in favor of withholding private information: the quality improving effect, which makes sellers more willing to invest in quality, and the sales increasing effect, which leads to more transactions on the platform.

The Role of Product and Market Information in an Online Marketplace

Although the online marketplaces have flourished, the role of product and market information in how it affects an online marketplace and how it can be leveraged to improve the sales or sales volume of the platform has not been explored in the prior research. We study how the provision of product and/or market information affects buyers' and sellers' behavior in an online marketplace by establishing the (Pareto-dominant) equilibrium for the sellers' pricing decisions under various information structures. Our main findings are as followings. First, we show that in equilibrium while sales volume of the platform increases in both the size of the buyers' pool and the size of the sellers' pool, sales increase only in the size of the buyers' pool and are unimodal in the size of the sellers' pool. Second, by analytically characterizing the platform's optimal information strategy as a function of the underlying market parameters and whether the platform's goal is to maximize sales or sales volume, we find that providing product and/or market information may backfire on the platform by jeopardizing its financial performance. Third, we demonstrate using numerical studies that information is more valuable to the platform when the goal of the platform is to maximize sales rather than sales volume, and when it faces a seller's market (i.e., demand-to-supply ratio is greater than one) rather than a buyer's market (i.e., demand-to-supply ratio is less than one).

The Beijing Platform for Action and Nutrition Education

The Beijing Platform for Action, a document adopted by nearly 190 participating governments at the Fourth World Conference on Women held in 1995 in Beijing, China, was analyzed for content related to food and nutrition. Words such as “nutrition,” “food,” and “hunger” were found in 6 of the 12 Platform sections on strategic objectives for the world's women. The Platform helps to demonstrate a universal recognition of nutritional concerns as part of necessary programs and actions for progress in girls’ and women's health and development. A call to “eliminate discrimination against girls in health and nutrition” was specifically included as one of the Platform's main strategic objectives. Nutrition educators and others involved in nutrition, health, and sustainable development have an important role to play in monitoring progress toward the achievement of the Beijing Platform's goals.