The Footprint of Factorization Models and Their Applications in Collaborative Filtering

Factorization models have been successfully applied to the recommendation problems and have significant impact to both academia and industries in the field of Collaborative Filtering ( CF ). However, the intermediate data generated in factorization models’ decision making process (or training process , footprint ) have been overlooked even though they may provide rich information to further improve recommendations. In this article, we introduce the concept of Convergence Pattern, which records how ratings are learned step-by-step in factorization models in the field of CF. We show that the concept of Convergence Patternexists in both the model perspective (e.g., classical Matrix Factorization ( MF ) and deep-learning factorization) and the training (learning) perspective (e.g., stochastic gradient descent ( SGD ), alternating least squares ( ALS ), and Markov Chain Monte Carlo ( MCMC )). By utilizing the Convergence Pattern, we propose a prediction model to estimate the prediction reliability of missing ratings and then improve the quality of recommendations. Two applications have been investigated: (1) how to evaluate the reliability of predicted missing ratings and thus recommend those ratings with high reliability. (2) How to explore the estimated reliability to adjust the predicted ratings to further improve the predication accuracy. Extensive experiments have been conducted on several benchmark datasets on three recommendation tasks: decision-aware recommendation, rating predicted, and Top- N recommendation. The experiment results have verified the effectiveness of the proposed methods in various aspects.

Assessment of genomic prediction reliability and optimization of experimental designs in multi-environment trials

Key message New forms of the coefficient of determination can help to forecast the accuracy of genomic prediction and optimize experimental designs in multi-environment trials with genotype-by-environment interactions. Abstract In multi-environment trials, the relative performance of genotypes may vary depending on the environmental conditions, and this phenomenon is commonly referred to as genotype-by-environment interaction (G$$\times$$ × E). With genomic prediction, G$$\times$$ × E can be accounted for by modeling the genetic covariance between trials, even when the overall experimental design is highly unbalanced between trials, thanks to the genomic relationship between genotypes. In this study, we propose new forms of the coefficient of determination (CD, i.e., the expected model-based square correlation between a genetic value and its corresponding prediction) that can be used to forecast the genomic prediction reliability of genotypes, both for their trial-specific performance and their mean performance. As the expected prediction reliability based on these new CD criteria is generally a good approximation of the observed reliability, we demonstrate that they can be used to optimize multi-environment trials in the presence of G$$\times$$ × E. In addition, this reliability may be highly variable between genotypes, especially in unbalanced designs with complex pedigree relationships between genotypes. Therefore, it can be useful for breeders to assess it before selecting genotypes based on their predicted genetic values. Using a wheat population evaluated both for simulated and phenology traits, and two maize populations evaluated for grain yield, we illustrate this approach and confirm the value of our new CD criteria.

Reliabilities of Genomic Prediction for Young Stock Survival Traits Using 54K SNP Chip Augmented With Additional Single-Nucleotide Polymorphisms Selected From Imputed Whole-Genome Sequencing Data

This study investigated effects of integrating single-nucleotide polymorphisms (SNPs) selected based on previous genome-wide association studies (GWASs), from imputed whole-genome sequencing (WGS) data, in the conventional 54K chip on genomic prediction reliability of young stock survival (YSS) traits in dairy cattle. The WGS SNPs included two groups of SNP sets that were selected based on GWAS in the Danish Holstein for YSS index (YSS_SNPs, n = 98) and SNPs chosen as peaks of quantitative trait loci for the traits of Nordic total merit index in Denmark–Finland–Sweden dairy cattle populations (DFS_SNPs, n = 1,541). Additionally, the study also investigated the possibility of improving genomic prediction reliability for survival traits by modeling the SNPs within recessive lethal haplotypes (LET_SNP, n = 130) detected from the 54K chip in the Nordic Holstein. De-regressed proofs (DRPs) were obtained from 6,558 Danish Holstein bulls genotyped with either 54K chip or customized LD chip that includes SNPs in the standard LD chip and some of the selected WGS SNPs. The chip data were subsequently imputed to 54K SNP together with the selected WGS SNPs. Genomic best linear unbiased prediction (GBLUP) models were implemented to predict breeding values through either pooling the 54K and selected WGS SNPs together as one genetic component (a one-component model) or considering 54K SNPs and selected WGS SNPs as two separate genetic components (a two-component model). Across all the traits, inclusion of each of the selected WGS SNP sets led to negligible improvements in prediction accuracies (0.17 percentage points on average) compared to prediction using only 54K. Similarly, marginal improvement in prediction reliability was obtained when all the selected WGS SNPs were included (0.22 percentage points). No further improvement in prediction reliability was observed when considering random regression on genotype code of recessive lethal alleles in the model including both groups of the WGS SNPs. Additionally, there was no difference in prediction reliability from integrating the selected WGS SNP sets through the two-component model compared to the one-component GBLUP.

Floating norms for individualising the ANB angle and the WITS appraisal in orthodontic cephalometric analysis based on guiding variables

Purpose The sagittal skeletal relationship of maxilla and mandible (skeletal class) can generally be determined via lateral cephalograms (ANB angle or Wits appraisal) by comparing measurements to empirical norms based on the respective population mean. However, values differing from these empirical norms also enable a therapeutically desired, normal class I occlusion depending on individual craniofacial pattern, thus requiring floating norms based on guiding variables. As available regression equations consider only few predictor variables and are not up-to-date regarding a contemporary patient collective, the aim of this study was to establish improved and extended regression equations for individualising the ANB angle and Wits appraisal. Methods This retrospective, cross-sectional multicentre study was based on 71 Caucasian male and female subjects of any age with normal dental occlusion. We cephalometrically analysed digitised pretreatment lateral radiographs and performed multiple linear regression analyses to identify suitable skeletal predictor variables for individualising the ANB angle and Wits appraisal. Results Inter- and intrarater reliability tests showed mostly perfect measurement concordance. Both original regression equations by Panagiotidis/Witt and Järvinen could be updated for a contemporary population with new regression coefficients. The equation for individualising the ANB could be further optimised in its prediction reliability by adding the skeletal predictor variables NL-NSL, NSBa, facial axis (Ricketts) and index (Hasund), whereas the recalculated Wits equation could not be further improved by additional guiding variables. Conclusions The improved regression formulae for individualising the ANB angle and Wits appraisal should help to improve the assessment of sagittal skeletal class in clinical orthodontic practice.

Outage prediction for ultra-reliable low-latency communications in fast fading channels

The addition of redundancy is a promising solution to achieve a certain quality of service (QoS) for ultra-reliable low-latency communications (URLLC) in challenging fast fading scenarios. However, adding more and more redundancy to the transmission results in severely increased radio resource consumption. Monitoring and prediction of fast fading channels can serve as the foundation of advanced scheduling. By choosing suitable resources for transmission, the resource consumption is reduced while maintaining the QoS. In this article, we present outage prediction approaches for Rayleigh and Rician fading channels. Appropriate performance metrics are introduced to show the suitability for URLLC radio resource scheduling. Outage prediction in the Rayleigh fading case can be achieved by adding a threshold comparison to state-of-the-art fading prediction approaches. A line-of-sight (LOS) component estimator is introduced that enables outage prediction in LOS scenarios. Extensive simulations have shown that under realistic conditions, effective outage probabilities of $$10^{-5}$$ 10 - 5 can be achieved while reaching up-state prediction probabilities of more than $${90}{\%}$$ 90 % . We show that the predictor can be tuned to satisfy the desired trade-off between prediction reliability and utilizability of the link. This enables our predictor to be used in future scheduling strategies, which achieve the challenging QoS of URLLC with fewer required redundancy.

Improving Reliability Estimation for Individual Numeric Predictions: A Machine Learning Approach

Numerical predictive modeling is widely used in different application domains. Although many modeling techniques have been proposed, and a number of different aggregate accuracy metrics exist for evaluating the overall performance of predictive models, other important aspects, such as the reliability (or confidence and uncertainty) of individual predictions, have been underexplored. We propose to use estimated absolute prediction error as the indicator of individual prediction reliability, which has the benefits of being intuitive and providing highly interpretable information to decision makers, as well as allowing for more precise evaluation of reliability estimation quality. As importantly, the proposed reliability indicator allows the reframing of reliability estimation itself as a canonical numeric prediction problem, which makes the proposed approach general-purpose (i.e., it can work in conjunction with any outcome prediction model), alleviates the need for distributional assumptions, and enables the use of advanced, state-of-the-art machine learning techniques to learn individual prediction reliability patterns directly from data. Extensive experimental results on multiple real-world data sets show that the proposed machine learning-based approach can significantly improve individual prediction reliability estimation as compared with a number of baselines from prior work, especially in more complex predictive scenarios.

Enhancing Soil and Water Assessment Tool Snow Prediction Reliability with Remote-Sensing-Based Snow Water Equivalent Reconstruction Product for Upland Watersheds in a Multi-Objective Calibration Process

Precipitation occurs in two basic forms defined as liquid state and solid state. Different from rain-fed watershed, modeling snow processes is of vital importance in snow-dominated watersheds. The seasonal snowpack is a natural water reservoir, which stores snow water in winter and releases it in spring and summer. The warmer climate in recent decades has led to earlier snowmelt, a decline in snowpack, and change in the seasonality of river flows. The Soil and Water Assessment Tool (SWAT) could be applied in the snow-influenced watershed because of its ability to simultaneously predict the streamflow generated from rainfall and from the melting of snow. The choice of parameters, reference data, and calibration strategy could significantly affect the SWAT model calibration outcome and further affect the prediction accuracy. In this study, SWAT models are implemented in four upland watersheds in the Tulare Lake Basin (TLB) located across the Southern Sierra Nevada Mountains. Three calibration scenarios considering different calibration parameters and reference datasets are applied to investigate the impact of the Parallel Energy Balance Model (ParBal) snow reconstruction data and snow parameters on the streamflow and snow water-equivalent (SWE) prediction accuracy. In addition, the watershed parameters and lapse rate parameters-led equifinality is also evaluated. The results indicate that calibration of the SWAT model with respect to both streamflow and SWE reference data could improve the model SWE prediction reliability in general. Comparatively, the streamflow predictions are not significantly affected by differently lumped calibration schemes. The default snow parameter values capture the extreme high flows better than the other two calibration scenarios, whereas there is no remarkable difference among the three calibration schemes for capturing the extreme low flows. The watershed and lapse rate parameters-induced equifinality affects the flow prediction more (Nash-Sutcliffe Efficiency (NSE) varies between 0.2–0.3) than the SWE prediction (NSE varies less than 0.1). This study points out the remote-sensing-based SWE reconstruction product as a promising alternative choice for model calibration in ungauged snow-influenced watersheds. The streamflow-reconstructed SWE bi-objective calibrated model could improve the prediction reliability of surface water supply change for the downstream agricultural region under the changing climate.