In the fast-moving consumer goods (FMCG) industry, deciding where to place physical assets, such as commercial beverage coolers, can directly impact revenue growth and execution efficiency. Although churn prediction and demand forecasting have been widely studied in B2B contexts, the use of machine learning to guide asset allocation remains relatively unexplored. This paper presents a framework focused on predicting which beverage clients are most likely to deliver strong returns in volume after receiving a cooler. Using a private dataset from a well-known Central American brewing and beverage company of 3,119 B2B traditional trade channel clients that received a cooler from 2022-01 to 2024-07, and tracking 12 months of sales transactions before and after cooler installation, three growth thresholds were defined: 10%, 30% and 50% growth in sales volume year over year. The analysis compares results of machine learning models such as XGBoost, LightGBM, and CatBoost combined with SHAP for interpretable feature analysis in order to have insights into improving business operations related to cooler allocation; the results show that the best model has AUC scores of 0.857, 0.877, and 0.898 across the thresholds on the validation set. Simulations suggest that this approach can improve ROI because it better selects potential clients to grow at the expected level and increases cost savings by not assigning clients that will not grow, compared to traditional volume-based approaches with substantial business management recommendations

We propose a novel prompt design paradigm that challenges conventional wisdom in large language model (LLM) prompting. While conventional wisdom prioritizes well-crafted instructions and demonstrations for in-context learning (ICL), we show that pruning random demonstrations into seemingly incoherent "gibberish" can remarkably improve performance across diverse tasks. Notably, the "gibberish" always matches or surpasses state-of-the-art automatic prompt optimization techniques, achieving substantial gains regardless of LLM alignment. Nevertheless, discovering an effective pruning strategy is non-trivial, as existing attribution methods and prompt compression algorithms fail to deliver robust results, let alone human intuition. In terms of this, we propose a self-discover prompt optimization framework, PromptQuine, an evolutionary search framework that automatically searches for the pruning strategy by itself using only low-data regimes. Much like the emergent complexity in nature--such as symbiosis and self-organization--arising in response to resource constraints, our framework evolves and refines unconventional yet highly effective prompts by leveraging only the tokens present within the context. We demonstrate its effectiveness across classification, multi-choice question answering, generation and math reasoning tasks across LLMs, while achieving decent runtime efficiency. We hope our findings can guide mechanistic studies on in-context learning, and provide a call to action, to pave the way for more open-ended search algorithms for more effective LLM prompting.

Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL) to table reasoning, achieving state-of-the-art performance. Through rigorous data preprocessing, reward design, and tailored training strategies, our method leverages simple rule-based outcome rewards to outperform SFT across multiple benchmarks. Unified training across diverse tasks enables Reasoning-Table to emerge as a robust table reasoning large language model, surpassing larger proprietary models like Claude-3.7-Sonnet by 4.0% on table reasoning benchmarks. The approach also achieves excellent performance on text-to-SQL tasks, reaching 68.3% performance on the BIRD dev dataset with a 7B model. Further experiments demonstrate that Reasoning-Table enhances the model's generalization capabilities and robustness.

The word creativity originally described a concept from human psychology, but in the realm of computational creativity (CC), it has become much more. The question of what creativity means when it is part of a computational system might be considered core to CC. Pinning down the meaning of creativity, and concepts like it, becomes salient when researchers port concepts from human psychology to computation, a widespread practice extending beyond CC into artificial intelligence (AI). Yet, the human processes shaping human-inspired computational systems have been little investigated. In this paper, we question which human literatures (social sciences, psychology, neuroscience) enter AI scholarship and how they are translated at the port of entry. This study is based on 22 in-depth, semi-structured interviews, primarily with human-inspired AI researchers, half of whom focus on creativity as a major research area. This paper focuses on findings most relevant to CC. We suggest that which human literature enters AI bears greater scrutiny because ideas may become disconnected from context in their home discipline. Accordingly, we recommend that CC researchers document the decisions and context of their practices, particularly those practices formalizing human concepts for machines. Publishing reflexive commentary on human elements in CC and AI would provide a useful record and permit greater dialogue with other disciplines.

The Internet generates large volumes of data at a high rate, in particular, posts on social networks. Although social network data has numerous semantic adulterations, and is not intended to be a source of geo-spatial information, in the text of posts we find pieces of important information about how people relate to their environment, which can be used to identify interesting aspects of how human beings interact with portions of land based on their activities. This research proposes a methodology for the identification of land uses using Natural Language Processing (NLP) from the contents of the popular social network Twitter. It will be approached by identifying keywords with linguistic patterns from the text, and the geographical coordinates associated with the publication. Context-specific innovations are introduced to deal with data across South America and, in particular, in the city of Arequipa, Peru. The objective is to identify the five main land uses: residential, commercial, institutional-governmental, industrial-offices and unbuilt land. Within the framework of urban planning and sustainable urban management, the methodology contributes to the optimization of the identification techniques applied for the updating of land use cadastres, since the results achieved an accuracy of about 90%, which motivates its application in the real context. In addition, it would allow the identification of land use categories at a more detailed level, in situations such as a complex/mixed distribution building based on the amount of data collected. Finally, the methodology makes land use information available in a more up-to-date fashion and, above all, avoids the high economic cost of the non-automatic production of land use maps for cities, mostly in developing countries.

This paper presents the PlanMiner-N algorithm, a domain learning technique based on the PlanMiner domain learning algorithm. The algorithm presented here improves the learning capabilities of PlanMiner when using noisy data as input. The PlanMiner algorithm is able to infer arithmetic and logical expressions to learn numerical planning domains from the input data, but it was designed to work under situations of incompleteness making it unreliable when facing noisy input data. In this paper, we propose a series of enhancements to the learning process of PlanMiner to expand its capabilities to learn from noisy data. These methods preprocess the input data by detecting noise and filtering it and study the learned action models learned to find erroneous preconditions/effects in them. The methods proposed in this paper were tested using a set of domains from the International Planning Competition (IPC). The results obtained indicate that PlanMiner-N improves the performance of PlanMiner greatly when facing noisy input data.

Surface roughness is primary measure of pavement performance that has been associated with ride quality and vehicle operating costs. Of all the surface roughness indicators, the International Roughness Index (IRI) is the most widely used. However, it is costly to measure IRI, and for this reason, certain road classes are excluded from IRI measurements at a network level. Higher levels of distresses are generally associated with higher roughness. However, for a given roughness level, pavement data typically exhibits a great deal of variability in the distress types, density, and severity. It is hypothesized that it is feasible to estimate the IRI of a pavement section given its distress types and their respective densities and severities. To investigate this hypothesis, this paper uses data from in-service pavements and machine learning methods to ascertain the extent to which IRI can be predicted given a set of pavement attributes. The results suggest that machine learning can be used reliably to estimate IRI based on the measured distress types and their respective densities and severities. The analysis also showed that IRI estimated this way depends on the pavement type and functional class. The paper also includes an exploratory section that addresses the reverse situation, that is, estimating the probability of pavement distress type distribution and occurrence severity/extent based on a given roughness level.

Designing adequate and precise neural architectures is a challenging task, often done by highly specialized personnel. AutoML is a machine learning field that aims to generate good performing models in an automated way. Spectral data such as those obtained from biological analysis have generally a lot of important information, and these data are specifically well suited to Convolutional Neural Networks (CNN) due to their image-like shape. In this work we present NASirt, an AutoML methodology based on Neural Architecture Search (NAS) that finds high accuracy CNN architectures for spectral datasets. The proposed methodology relies on the Item Response Theory (IRT) for obtaining characteristics from an instance level, such as discrimination and difficulty, and it is able to define a rank of top performing submodels. Several experiments are performed in order to demonstrate the methodology's performance with different spectral datasets. Accuracy results are compared to other benchmarks methods, such as a high performing, manually crafted CNN and the Auto-Keras AutoML tool. The results show that our method performs, in most cases, better than the benchmarks, achieving average accuracy as high as 96.96%.

This paper deals with the arrow of complexification of engineering. We claim that the complexification of engineering consists in (a) that shift throughout which engineering becomes a science; thus it ceases to be a (mere) praxis or profession; (b) becoming a science, engineering can be considered as one of the sciences of complexity. In reality, the complexification of engineering is the process by which engineering can be studied, achieved and understood in terms of knowledge, and not of goods and services any longer. Complex engineered systems and bio-inspired engineering are so far the two expressions of a complex engineering.

Modern evolutionary computation utilizes heuristic optimizations based upon concepts borrowed from the Darwinian theory of natural selection. We believe that a vital direction in this field must be algorithms that model the activity of genomic parasites, such as transposons, in biological evolution. This publication is our first step in the direction of developing a minimal assortment of algorithms that simulate the role of genomic parasites. Specifically, we started in the domain of genetic algorithms (GA) and selected the Artificial Ant Problem as a test case. We define these artificial transposons as a fragment of an ant's code that possesses properties that cause it to stand apart from the rest. We concluded that artificial transposons, analogous to real transposons, are truly capable of acting as intelligent mutators that adapt in response to an evolutionary problem in the course of co-evolution with their hosts.