Leveraging fine-grained mobile data for churn detection through Essence Random Forest

AbstractThe rise of unstructured data leads to unprecedented opportunities for marketing applications along with new methodological challenges to leverage such data. In particular, redundancy among the features extracted from this data deserves special attention as it might prevent current methods to benefit from it. In this study, we propose to investigate the value of multiple fine-grained data sources i.e. websurfing, use of applications and geospatial mobility for churn detection within telephone companies. This value is analysed both in substitution and in complement to the value of the well-known communication network. What is more, we also suggest an adaptation of the Random Forest algorithm called Essence Random Forest designed to better address redundancy among extracted features. Analysing fine-grained data of a telephone company, we first find that geo-spatial mobility data might be a good long term alternative to the classical communication network that might become obsolete due to the competition with digital communications. Then, we show that, on the short term, these alternative fine-grained data might complement the communication network for an improved churn detection. In addition, compared to Random Forest and Extremely Randomized Trees, Essence Random Forest better leverages the value of unstructured data by offering an enhanced churn detection regardless of the addressed perspective i.e. substitution or complement. Finally, Essence Random Forest converges faster to stable results which is a salient property in a resource constrained environment.

Download Full-text

Microstructural Investigations on Plasticity of Lime-Treated Soils

Minerals ◽

10.3390/min10050386 ◽

2020 ◽

Vol 10 (5) ◽

pp. 386

Author(s):

Enza Vitale ◽

Dimitri Deneele ◽

Giacomo Russo

Keyword(s):

Liquid Limit ◽

Small Scale ◽

Plastic Behavior ◽

Short Term ◽

Clay Particles ◽

Fine Grained ◽

Surface Charge Distribution ◽

Plastic Changes ◽

Interparticle Repulsion

The surface charge distribution of clay particles governs the interparticle forces and their arrangement in clay-water systems. The plasticity properties are the consequences of the interaction at the microscopic scale, even if they are traditionally linked to the mechanical properties of fine-grained soils. In the paper, the plasticity modifications induced by the addition of lime were experimentally investigated for two different clays (namely kaolinite and bentonite) in order to gain microstructural insights of the mechanisms affecting their plastic behavior as a function of the lime content and curing time. Zeta potential and dynamic light scattering measurements, as well as thermogravimetric analyses, highlighted the mechanisms responsible for the plastic changes at a small scale. The increase of the interparticle attraction forces due to the addition of lime increased the liquid and plastic limits of kaolinite in the short term, without significant changes in the long term due to the low reactivity of the clay in terms of pozzolanic reactions. The addition of lime to bentonite resulted in a decrease of interparticle repulsion double layer interactions. Rearrangement of the clay particles determined a reduction of the liquid limit and an increase of the plastic limit of the treated clays in the very short term. Precipitation of the bonding compounds due to pozzolanic reactions increased both the liquid and plastic limits over the time.

Download Full-text

On-Side fighting in civil war: The logic of mortal alignment in Syria

Rationality and Society ◽

10.1177/1043463120966989 ◽

2020 ◽

Vol 32 (4) ◽

pp. 402-460

Author(s):

Jonah Schulhofer-Wohl

Keyword(s):

Civil Wars ◽

Political Competition ◽

Spatial And Temporal Variation ◽

Armed Groups ◽

Short Term ◽

Term Survival ◽

Fine Grained ◽

Trade Offs ◽

Short Term Survival

On-side fighting – outright violence between armed groups aligned on the same side of a civil war’s master cleavage – represents a devastating breakdown in cooperation. Its humanitarian consequences are also grave. But it has been under-recognized empirically and therefore under-theorized by scholars to date. This article remedies the omission. Existing research can be extrapolated to produce candidate explanations, but these overlook spatial and temporal variation in on-side fighting within a war. I provide a theory that accounts for this ebb and flow. On-side fighting hinges on belligerents’ trade-offs between short-term survival and long-term political objectives. Enemy threats to survival underpin on-side cooperation; in their absence, belligerents can pursue political gains against on-side competitors. I evaluate this threat-absence theory using evidence from the ongoing Syrian Civil War’s first years. Fine-grained fatalities data capture fluctuating enemy threats to on-side groups’ survival and situate on-side fighting and its absence. Findings support threat-absence theory and contribute to research on warfighting and political competition in civil wars and to the study of coalition dynamics in other settings, including elections and legislatures.

Download Full-text

Personalized, Sequential, Attentive, Metric-Aware Product Search

ACM Transactions on Information Systems ◽

10.1145/3473337 ◽

2022 ◽

Vol 40 (2) ◽

pp. 1-29

Author(s):

Yaoxin Pan ◽

Shangsong Liang ◽

Jiaxin Ren ◽

Zaiqiao Meng ◽

Qiang Zhang

Keyword(s):

Triangle Inequality ◽

Historical Data ◽

Short Term ◽

Fine Grained ◽

Different Types ◽

Benchmark Datasets ◽

Product Search ◽

Visualization Experiments ◽

Ranked List

The task of personalized product search aims at retrieving a ranked list of products given a user’s input query and his/her purchase history. To address this task, we propose the PSAM model, a Personalized, Sequential, Attentive and Metric-aware (PSAM) model, that learns the semantic representations of three different categories of entities, i.e., users, queries, and products, based on user sequential purchase historical data and the corresponding sequential queries. Specifically, a query-based attentive LSTM (QA-LSTM) model and an attention mechanism are designed to infer users dynamic embeddings, which is able to capture their short-term and long-term preferences. To obtain more fine-grained embeddings of the three categories of entities, a metric-aware objective is deployed in our model to force the inferred embeddings subject to the triangle inequality, which is a more realistic distance measurement for product search. Experiments conducted on four benchmark datasets show that our PSAM model significantly outperforms the state-of-the-art product search baselines in terms of effectiveness by up to 50.9% improvement under NDCG@20. Our visualization experiments further illustrate that the learned product embeddings are able to distinguish different types of products.

Download Full-text

Assessing supply chain risk for apparel production in low cost countries using newsfeed analysis

Supply Chain Management An International Journal ◽

10.1108/scm-11-2019-0423 ◽

2020 ◽

Vol 25 (6) ◽

pp. 803-821 ◽

Cited By ~ 2

Author(s):

Robert Handfield ◽

Hang Sun ◽

Lori Rothenberg

Keyword(s):

Supply Chain ◽

Low Cost ◽

Developed Countries ◽

Unstructured Data ◽

Risk Scores ◽

Supply Chain Risk ◽

Short Term ◽

Workplace Issues ◽

Content Type

Purpose With the growth of unstructured data, opportunities to generate insights into supply chain risks in low cost countries (LCCs) are emerging. Sourcing risk has primarily focused on short-term mitigation. This paper aims to offer an approach that uses newsfeed data to assess regional supply base risk in LCC’s for the apparel sector, which managers can use to plan for future risk on a long-term planning horizon. Design/methodology/approach This paper demonstrates that the bulk of supplier risk assessments focus on short-term responses to disruptions in developed countries, revealing a gap in assessments of long-term risks for supply base expansion in LCCs. This paper develops an approach for predicting and planning for long-term supply base risk in LCC’s to address this shortfall. A machine-based learning algorithm is developed that uses the analysis of competing hypotheses heuristic to convert data from multiple news feeds into numerical risk scores and visual maps of supply chain risk. This paper demonstrates the approach by converting large amounts of unstructured data into two measures, risk impact and risk probability, leading to visualization of country-level supply base risks for a global apparel company. Findings This paper produced probability and impact scores for 23 distinct supply base risks across 10 countries in the apparel sector. The results suggest that the most significant long-term risks of supply disruption for apparel in LCC’s are human resource regulatory risks, workplace issues, inflation costs, safety violations and social welfare violations. The results suggest that apparel brands seeking suppliers in the regions of Cambodia, India, Bangladesh, Brazil and Vietnam should be aware of the significant risks in these regions that may require mitigative action. Originality/value This approach establishes a novel approach for objectively projecting future global sourcing risk, and yields visually mapped outcomes that can be applied in forecasting and planning for future risks when considering sourcing locations in LCC’s.

Download Full-text

Kalman Filter Based Short Term Prediction Model for COVID-19 Spread

10.1101/2020.05.30.20117416 ◽

2020 ◽

Cited By ~ 1

Author(s):

Suraj Kumar ◽

Koushlendra Kumar Singh ◽

Prachi Dixit ◽

Manish Kumar Bajpai

Keyword(s):

Kalman Filter ◽

Random Forest ◽

Test Data ◽

Pearson Correlation ◽

Medical Emergency ◽

Contributing Factors ◽

Short Term ◽

Long Term Forecasting ◽

Short Term Prediction

AbstractCOVID-19 has emerged as global medical emergency in recentdecades. The spread scenario of this pandemic has shown many variations. Keeping all this in mind, this article is written after various studies and analysis on the latest data on COVID-19 spread, which also includes the demographic and environmental factors. After gathering data from various resources, all data are integrated and passed into different Machine Learning Models to check the fit. Ensemble Learning Technique,Random Forest, gives a good evaluation score on the test data. Through this technique, various important factors are recognised and their contribution to the spread is analysed. Also, linear relationship between various features is plotted through heatmap of Pearson Correlation matrix. Finally, Kalman Filter is used to estimate future spread of COVID19, which shows good result on test data. The inferences from Random Forest feature importance and Pearson Correlation gives many similarities and some dissimilarities, and these techniques successfully identify the different contributing factors. The Kalman Filter gives a satisfying result for short term estimation, but not so good performance for long term forecasting. Overall, the analysis, plots, inferences and forecast are satisfying and can help a lot in fighting the spread of the virus.

Download Full-text

Conceptual short-term memory (CSTM) supports core claims of Christiansen and Chater

Behavioral and Brain Sciences ◽

10.1017/s0140525x15000928 ◽

2016 ◽

Vol 39 ◽

Author(s):

Mary C. Potter

Keyword(s):

Working Memory ◽

Rapid Serial Visual Presentation ◽

Language Comprehension ◽

Short Term Memory ◽

Visual Presentation ◽

Long Term Memory ◽

Short Term ◽

Term Memory ◽

Use Of Knowledge

AbstractRapid serial visual presentation (RSVP) of words or pictured scenes provides evidence for a large-capacity conceptual short-term memory (CSTM) that momentarily provides rich associated material from long-term memory, permitting rapid chunking (Potter 1993; 2009; 2012). In perception of scenes as well as language comprehension, we make use of knowledge that briefly exceeds the supposed limits of working memory.

Download Full-text

Ultrastructural investigations of MDL 19,660-induced effects on the canine platelet and megakaryocyte

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100159412 ◽

1990 ◽

Vol 48 (3) ◽

pp. 374-375

Author(s):

D.E. Loudy ◽

J. Sprinkle-Cavallo ◽

J.T. Yarrington ◽

F.Y. Thompson ◽

J.P. Gibson

Keyword(s):

Antidepressant Drug ◽

Beagle Dogs ◽

Long Term Effects ◽

Short Term ◽

Platelet Counts ◽

Toxicological Studies ◽

Induced Aggregation ◽

Internal Architecture

Previous short term toxicological studies of one to two weeks duration have demonstrated that MDL 19,660 (5-(4-chlorophenyl)-2,4-dihydro-2,4-dimethyl-3Hl, 2,4-triazole-3-thione), an antidepressant drug, causes a dose-related thrombocytopenia in dogs. Platelet counts started to decline after two days of dosing with 30 mg/kg/day and continued to decrease to their lowest levels by 5-7 days. The loss in platelets was primarily of the small discoid subpopulation. In vitro studies have also indicated that MDL 19,660: does not spontaneously aggregate canine platelets and has moderate antiaggregating properties by inhibiting ADP-induced aggregation. The objectives of the present investigation of MDL 19,660 were to evaluate ultrastructurally long term effects on platelet internal architecture and changes in subpopulations of platelets and megakaryocytes.Nine male and nine female beagle dogs were divided equally into three groups and were administered orally 0, 15, or 30 mg/kg/day of MDL 19,660 for three months. Compared to a control platelet range of 353,000- 452,000/μl, a doserelated thrombocytopenia reached a maximum severity of an average of 135,000/μl for the 15 mg/kg/day dogs after two weeks and 81,000/μl for the 30 mg/kg/day dogs after one week.

Download Full-text

Comparison of Auditory, Language, Memory, and Attention Abilities in Children With and Without Listening Difficulties

American Journal of Audiology ◽

10.1044/2020_aja-20-00018 ◽

2020 ◽

Vol 29 (4) ◽

pp. 710-727

Author(s):

Beula M. Magimairaj ◽

Naveen K. Nagaraj ◽

Alexander V. Sergeev ◽

Natalie J. Benafield

Keyword(s):

Auditory Processing ◽

Short Term Memory ◽

Group Differences ◽

Long Term Memory ◽

Short Term ◽

Significant Group ◽

Term Memory ◽

Memory And Attention ◽

Speed And Accuracy

Objectives School-age children with and without parent-reported listening difficulties (LiD) were compared on auditory processing, language, memory, and attention abilities. The objective was to extend what is known so far in the literature about children with LiD by using multiple measures and selective novel measures across the above areas. Design Twenty-six children who were reported by their parents as having LiD and 26 age-matched typically developing children completed clinical tests of auditory processing and multiple measures of language, attention, and memory. All children had normal-range pure-tone hearing thresholds bilaterally. Group differences were examined. Results In addition to significantly poorer speech-perception-in-noise scores, children with LiD had reduced speed and accuracy of word retrieval from long-term memory, poorer short-term memory, sentence recall, and inferencing ability. Statistically significant group differences were of moderate effect size; however, standard test scores of children with LiD were not clinically poor. No statistically significant group differences were observed in attention, working memory capacity, vocabulary, and nonverbal IQ. Conclusions Mild signal-to-noise ratio loss, as reflected by the group mean of children with LiD, supported the children's functional listening problems. In addition, children's relative weakness in select areas of language performance, short-term memory, and long-term memory lexical retrieval speed and accuracy added to previous research on evidence-based areas that need to be evaluated in children with LiD who almost always have heterogenous profiles. Importantly, the functional difficulties faced by children with LiD in relation to their test results indicated, to some extent, that commonly used assessments may not be adequately capturing the children's listening challenges. Supplemental Material https://doi.org/10.23641/asha.12808607

Download Full-text