Deep learning in business analytics: A clash of expectations and reality

Schmitt, Marc

doi:10.1016/j.jjimei.2022.100146

Cited by 45 publications

(16 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work we do not consider deep-learning predicting algorithms. In the social sciences and business analytics data context, deep learning models have been proved to have predictive accuracy generally comparable to other ML methods [ 46 ]. This depends on the fact that deep-learning models improve prediction by exploiting some kind of ordering in the data.…”

Section: Resultsmentioning

confidence: 99%

Link prediction and feature relevance in knowledge networks: A machine learning approach

Zinilli,

Cerulli

2023

PLoS ONE

View full text Add to dashboard Cite

We propose a supervised machine learning approach to predict partnership formation between universities. We focus on successful joint R&D projects funded by the Horizon 2020 programme in three research domains: Social Sciences and Humanities, Physical and Engineering Sciences, and Life Sciences. We perform two related analyses: link formation prediction, and feature importance detection. In predicting link formation, we consider two settings: one including all features, both exogenous (pertaining to the node) and endogenous (pertaining to the network); and one including only exogenous features (thus removing the network attributes of the nodes). Using out-of-sample cross-validated accuracy, we obtain 91% prediction accuracy when both types of attributes are used, and around 67% when using only the exogenous ones. This proves that partnership predictive power is on average 24% larger for universities already incumbent in the programme than for newcomers (for which network attributes are clearly unknown). As for feature importance, by computing super-learner average partial effects and elasticities, we find that the endogenous attributes are the most relevant in affecting the probability to generate a link, and observe a largely negative elasticity of the link probability to feature changes, fairly uniform across attributes and domains.

show abstract

Section: Resultsmentioning

confidence: 99%

Link prediction and feature relevance in knowledge networks: A machine learning approach

Zinilli,

Cerulli

2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…This study uses the gradient boosting version implemented by Malohlava and Candel [48], which is based on Hastie et al, [47]. GBM can be considered state-of-the-art when it comes to prediction accuracy for supervised learning problems on structured data sets [49].…”

Section: Machine Learning Modelsmentioning

confidence: 99%

Securing the Digital World: Protecting Smart Infrastructures and Digital Industries with Artificial Intelligence (Ai)-Enabled Malware and Intrusion Detection

Schmitt

2023

Preprint

View full text Add to dashboard Cite

“…Using DL can effectively find the regularity behind a large number of data, provide the hidden knowledge and means in the data, and eliminate the phenomenon of data "explosion but lack of knowledge" [2]. In order to better assist investors to evaluate and make decisions on financial data, this paper puts forward the need to build a reliable and effective financial data forecasting model, and on the basis of financial data analysis, integrates DL algorithm to analyze financial data [3]. The real decision-making based on data analysis is mainly concentrated in the banking, insurance, telecommunications and e-commerce industries, and has not yet expanded to all areas of operation management.…”

Section: Introductionmentioning

confidence: 99%

Research on Business Data Analysis and Mining based on Deep Learning

Gao

2023

TCSISR

View full text Add to dashboard Cite

At present, the database system can efficiently realize the functions of data entry, query and statistics, but it can't find the rules of relationships in the database, and can't predict the future development trend according to the existing data. Using data mining technology, we can effectively find the regularity behind a large number of data, provide the hidden knowledge and means in the data, and eliminate the phenomenon of data "explosion but lack of knowledge". Based on DL (Deep Learning), this paper studies the analysis and mining of commercial data. In order to better assist investors to evaluate and make decisions on financial data, it puts forward the need to build a reliable and effective financial data forecasting model. In the original data obtained, it is necessary to interpolate by certain methods in data cleaning, and some repeated data will be duplicated. This paper analyzes and makes full use of these massive commercial information through DL, finds out the potential laws of business and market operation, and finds some unknown and hidden useful information from it, which helps enterprises to grasp the development direction of the industry and sales market from a macro perspective and better serve the vast number of consumers.

show abstract

Deep learning in business analytics: A clash of expectations and reality

Cited by 45 publications

References 28 publications

Link prediction and feature relevance in knowledge networks: A machine learning approach

Link prediction and feature relevance in knowledge networks: A machine learning approach

Securing the Digital World: Protecting Smart Infrastructures and Digital Industries with Artificial Intelligence (Ai)-Enabled Malware and Intrusion Detection

Research on Business Data Analysis and Mining based on Deep Learning

Contact Info

Product

Resources

About