The rapid growth of e-commerce has significantly increased the demand for advanced techniques to address specific tasks in field. In this paper, we present a brief survey machine learning and deep context e-commerce, focusing on years 2018–2023 Google Scholar search, with aim identifying state-of-the-art approaches, main topics, potential challenges We first introduce applied techniques, spanning from support vector machines, decision trees, random forests conventional neural networks,...

The high penetration of distributed energy resources poses significant challenges to the dispatch and operation power systems. Improving accuracy short-term load forecasting (STLF) can optimize grid management, thus leading increased economic social benefits. Currently, some simple AI hybrid models have issues deal with struggle multivariate dependencies, long-term nonlinear relationships. This paper proposes a novel model for that integrates multiple Lasso regression using stacking...

The essential role of the particular families capacities and capacity identification methods is to help decision maker deal with exponential complexity inherent in construction process capacity. 2-additive appear be most popular among since they permit model interactions between criteria while preserving simplicity. Besides preference respect criteria, also need provide desired overall evaluations alternatives learning set, which a time-consuming task for maker. In this paper, we propose...

In this paper, the Choquet integral and interval neutrosophic set theory are combined to make multi-criteria decision for problems under fuzzy environment. Firstly, a ranking index is proposed according its geometrical structure, an approach comparing two neutro sophic numbers given. Then, ≤L implied operation-invariant total order which satisfies order-preserving condition proposed. Secondly, number (INNCI) operator established detailed discussion on aggregation properties presented....

The random generation of fuzzy measures under complex linear constraints holds significance in various fields, including optimization solutions, machine learning, decision making, and property investigation. However, most existing methods primarily focus on addressing the monotonicity normalization conditions inherent construction measures, rather than that are crucial for representing special families additional preference information. In this paper, we present two categories to address...

We review recent literature on three aspects of fuzzy measures: their representations, learning optimal measures and random generation various types measures. These are interdependent: methods depend representation, may also include as one the steps, other hand different representations affect methods, while plays an important role in simulation studies for post-hoc analysis sets learned from data problem-specific constraints. Explicit modelling interactions between decision variables is a...

Multicriteria correlation preference information (MCCPI) refers to a special type of 2-dimensional explicit information: the importance and interaction preferences regarding multiple dependent decision criteria. A few identification models have been established implemented transform MCCPI into most satisfactory 2-additive capacity. However, as one commonly accepted particular capacity, capacity only takes account 2-order interactions ignores higher order interactions, which is not always...

The probabilistic simultaneous interaction index has been widely adopted to measure the among decision criteria. However, this type of indices sometimes fails reflect kind associated with nonadditivity a fuzzy (capacity). For example, any universal set criteria w.r.t. strictly superadditive capacity is not always positive. main reason that generalizes notion value by replacing marginal contribution single criterion subset. In paper, we reform generalization process and replace bipartition...

Abstract The decision maker's preference information on the importance and interaction of criteria can be explicitly described by probabilistic indices in framework capacity based multicriteria analysis. In this paper, we first investigate some properties empty set, propose maximum minimum set principles identification methods, which considered as comprehensive trend oriented methods. Then, introducing deviation variables, goal constraints, well objective function, give a new more flexible...

Nonadditive robust ordinal regression (NAROR) is a widely adopted approach to analyze and reveal the dominance relationships among all decision alternatives based on nonadditive measures, called capacities. In this paper, we first investigate some advantages of nonadditivity index as an explicit interaction index, compared with traditional probabilistic simultaneous indices, show that can serve equivalent representation capacity. Then enhance NAROR method by using well multiple-goal linear...

In the field of multicriteria decision analysis, most distinctive characteristic monotone measure, or called nonadditive fuzzy capacity, is that it can adequately and flexibly describe interactions between criteria. Traditionally, intera ction described with measure be measured by various kinds probabilistic interaction indices, among which Shapley index famous suitable one for making. Inspired marginal multiple criteria, a core notion we define extremely positive negative cases find...

In the literature [40], authors proposed sum interaction index and discussed its basic mathematical properties. And by some comparison analyses, demonstrated that can be taken as an alternative of probabilistic to measure inter action phenomenon multiple decision criteria. this paper, we further investigate properties with respect particular families monotone measures, such λ-monotone possibility k-additive p-symmetric k-tolerant k-intolerant measures. Some illustrative examples are also...