scholarly journals Can Computational Antitrust Succeed?

10.51868/3 ◽  
2021 ◽  
pp. 38-51
Author(s):  
Daryl Lim
Keyword(s):  
Neural Network ◽  
Economic Theory ◽  
Fast Moving ◽  
Recommendation System ◽  
Antitrust Policy ◽  
Antitrust Law ◽  
Trial And Error ◽  
Weakest Link ◽  
Rule Of Reason ◽  
The Given

Computational antitrust comes to us at a time when courts and agencies are underfunded and overwhelmed, all while having to apply indeterminate rules to massive amounts of information in fast-moving markets. In the same way that Amazon disrupted e-commerce through its inventory and sales algorithms and TikTok’s progressive recommendation system keeps users hooked, computational antitrust holds the promise to revolutionize antitrust law. Implemented well, computational antitrust can help courts curate and refine precedential antitrust cases, identify anticompetitive effects, and model innovation effects and counterfactuals in killer acquisition cases. The beauty of AI is that it can reach outcomes humans alone cannot define as “good” or “better” as the untrained neural network interrogates itself via the process of trial and error. The maximization process is dynamic, with the AI being capable of scouring options to optimize the best rewards under the given circumstances, mirroring how courts operationalize antitrust policy–computing the expected reward from executing a policy in a given environment. At the same time, any system is only as good as its weakest link, and computational antitrust is no exception. The synergistic possibilities that humans and algorithms offer depend on their interplay. Humans may lean on ideology as a heuristic when they must interpret the rule of reason according to economic theory and evidence. For this reason, it becomes imperative to understand, mitigate, and, where appropriate, harness those biases.

scholarly journals Code Edit Recommendation Using a Recurrent Neural Network

2021 ◽  
Vol 11 (19) ◽  
pp. 9286
Author(s):  
Seonah Lee ◽  
Jaejun Lee ◽  
Sungwon Kang ◽  
Jongsun Ahn ◽  
Heetae Cho
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Association Rule ◽  
Association Rule Mining ◽  
Recommendation System ◽  
Software Evolution ◽  
Rule Mining ◽  
Mining Technique ◽  
Recommendation Accuracy ◽  
The Given

When performing software evolution tasks, developers spend a significant amount of time looking for files to modify. By recommending files to modify, a code edit recommendation system reduces the developer’s navigation time when conducting software evolution tasks. In this paper, we propose a code edit recommendation method using a recurrent neural network (CERNN). CERNN forms contexts that maintain the sequence of developers’ interactions to recommend files to edit and stops recommendations when the first recommendation becomes incorrect for the given evolution task. We evaluated our method by comparing it with the state-of-the-art method MI-EA that was developed based on the association rule mining technique. The result shows that our proposed method improves the average recommendation accuracy by approximately 5% over MI-EA (0.64 vs. 0.59 F-score).

Rule of Reason (ROR): Gains and Risks

2018 ◽  
Vol 2018 (1) ◽  
pp. 65-81
Author(s):  
Andrej Makarov
Keyword(s):  
Economic Theory ◽  
Antitrust Policy ◽  
Negative Effects ◽  
Rule Of Reason ◽  
The Us ◽  
Rapid Formation ◽  
Per Se ◽  
Type 2 Errors

This article discusses the rapid formation of the Rule of Reason (ROR) approach in antitrust policy in the field of anti — competitive agreements. In many countries (the US, EU) there was a significant reduction of the use of per se approach (prohibition on the base of formal characteristics) in favor of the ROR approach, nowadays agreements are usually permitted or prohibited on the basis of the analysis of positive and negative effects. The article analyzes and summarizes the experience of these jurisdictions in the development of the ROR approach, the chronology for agreements of various types (horizontal, vertical agreements). The role of discussions in economic theory in this process was provided the argumentation for the expansion of effects evaluation. At the same time, the article examines the problems of this transformation, taking into account the problems of legal uncertainty, growing risks of type 2 errors.

scholarly journals News recommendation system using machine learning

2018 ◽  
Vol 7 (2.18) ◽  
pp. 32
Author(s):  
Neha Rani ◽  
Sudhir Sudhir Pathak
Keyword(s):  
Neural Network ◽  
Recommendation System ◽  
High Accuracy ◽  
Svm Classifier ◽  
Financial News ◽  
The Neural Network ◽  
Market Forecast ◽  
News Recommendation ◽  
Weighted Values ◽  
The Given

The forecasting of financial news is yet becoming the main issue to divide the new into different classes on the basis of present time series. Moreover, it might be utilized for predicting and analyzing the stock market for the particular industry. Thus, the new content is significantly important to influence market forecast report. In this paper, the financial news from four countries namely America, Australia, India and South Africa along with their stop words are consider. The words along with their weighted values are determined and then the neural network is trained. Here, artificial neural network is used for classifying the appropriate results for the given input data. At last the comparison of ANN with SVM is shown. Experiments show that the ANN classification provides high accuracy to predict the news than the SVM classifier. 

scholarly journals A Two-Stage Neural Network-Based Cold Start Item Recommender

2021 ◽  
Vol 11 (9) ◽  
pp. 4243
Author(s):  
Chieh-Yuan Tsai ◽  
Yi-Fan Chiu ◽  
Yu-Jen Chen
Keyword(s):  
Neural Network ◽  
Recommendation System ◽  
Service Providers ◽  
Cold Start ◽  
Computational Time ◽  
Two Stage ◽  
The Neural Network ◽  
Textual Description ◽  
Recommendation Algorithms ◽  
Content Information

Nowadays, recommendation systems have been successfully adopted in variant online services such as e-commerce, news, and social media. The recommenders provide users a convenient and efficient way to find their exciting items and increase service providers’ revenue. However, it is found that many recommenders suffered from the cold start (CS) problem where only a small number of ratings are available for some new items. To conquer the difficulties, this research proposes a two-stage neural network-based CS item recommendation system. The proposed system includes two major components, which are the denoising autoencoder (DAE)-based CS item rating (DACR) generator and the neural network-based collaborative filtering (NNCF) predictor. In the DACR generator, a textual description of an item is used as auxiliary content information to represent the item. Then, the DAE is applied to extract the content features from high-dimensional textual vectors. With the compact content features, a CS item’s rating can be efficiently derived based on the ratings of similar non-CS items. Second, the NNCF predictor is developed to predict the ratings in the sparse user–item matrix. In the predictor, both spare binary user and item vectors are projected to dense latent vectors in the embedding layer. Next, latent vectors are fed into multilayer perceptron (MLP) layers for user–item matrix learning. Finally, appropriate item suggestions can be accurately obtained. The extensive experiments show that the DAE can significantly reduce the computational time for item similarity evaluations while keeping the original features’ characteristics. Besides, the experiments show that the proposed NNCF predictor outperforms several popular recommendation algorithms. We also demonstrate that the proposed CS item recommender can achieve up to 8% MAE improvement compared to adding no CS item rating.

Building Electronic Commerce Recommendation System Based on Ontology Learning and BP Neural Network

2013 ◽  
Vol 718-720 ◽  
pp. 1961-1966
Author(s):  
Hong Sheng Xu ◽  
Qing Tan
Keyword(s):  
Neural Network ◽  
Electronic Commerce ◽  
Bp Neural Network ◽  
Optimization Problem ◽  
Recommendation System ◽  
High Efficiency ◽  
Ontology Learning ◽  
The Neural Network ◽  
Network Process ◽  
Hidden Layer

Electronic commerce recommendation system can effectively retain user, prevent users from erosion, and improve e-commerce system sales. BP neural network using iterative operation, solving the weights of the neural network and close values to corresponding network process of learning and memory, to join the hidden layer nodes of the optimization problem of adjustable parameters increase. Ontology learning is the use of machine learning and statistical techniques, with automatic or semi-automatic way, from the existing data resources and obtaining desired body. The paper presents building electronic commerce recommendation system based on ontology learning and BP neural network. Experimental results show that the proposed algorithm has high efficiency.

Recommendation System for Material Scientists Based on Deep Learn Neural Network

2018 ◽  
pp. 216-223 ◽  
Author(s):  
Andrei Kliuev ◽  
Roman Klestov ◽  
Maria Bartolomey ◽  
Aleksei Rogozhnikov
Keyword(s):  
Neural Network ◽  
Recommendation System

scholarly journals Comparison Study on Improved Movie Recommender Systems

Webology ◽  
2021 ◽  
Vol 18 (Special Issue 04) ◽  
pp. 1470-1478
Author(s):  
R. Lavanya ◽  
Ebani Gogia ◽  
Nihal Rai
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Recommendation System ◽  
Singular Value ◽  
Experimental Result ◽  
Comparison Study ◽  
Deep Learning Neural Network ◽  
Value Decomposition ◽  
Crucial Part

Recommendation system is a crucial part of offering items especially in services that offer streaming. For streaming movie services on OTT, RS are a helping hand for users in finding new movies for leisure. In this paper, we propose a machine learning an approach based on auto encoders to produce a CF system which outputs movie rating for a user based on a huge DB of ratings from other users. Utilising Movie Lens dataset, we explore the use of deep learning neural network based Stacked Auto encoders to predict user s ratings on new movies, thereby enabling movie recommendations. We consequently implement Singular Value Decomposition (SVD) to recommend movies to users. The experimental result showcase that our R S out performs a user-based neighbourhood baseline in terms of MSE on predicted ratings and in a survey in which user judge between recommendation s from both systems.

Sign in / Sign up

Export Citation Format

Share Document