UNDERSTANDING CRIMINAL GROUPS AS SOCIAL NETWORKS HAS LED TO THE DESIGN OF POWERFUL SYSTEMS FOR DECISION SUPPORT IN CRIMINAL INVESTIGATIVE WORK. TOOLS USING THE METHODS OF SOCIAL NETWORK ANALYSIS HAVE PROVEN PARTICULARLY EFFECTIVE IN THE IDENTIFICATION OF ASSOCIATIONS BETWEEN INDIVIDUALS WHOSE RELATIONSHIPS ARE NOT OTHERWISE EVIDENT. THIS IDENTIFICATION IS TYPICALLY BASED ON THE LINKS BETWEEN INDIVIDUALS AND DOES NOT ACCOUNT FOR OTHER RELEVANT INFORMATION, SUCH AS INDIVIDUAL ATTRIBUTES. THE PRESENT STUDY PROPOSES A NEW MODEL FOR IDENTIFYING CRIMINAL ASSOCIATIONS THAT INCORPORATES THIS TYPE OF DATA. BUILT AROUND A LINEAR ASSOCIATION MODEL, THIS APPROACH IDENTIFIES THE PRINCIPAL ASSOCIATION BETWEEN TWO INDIVIDUALS. ASSUMING ONE OF THE INDIVIDUALS AS THE CRIME PLANNER, THE APPROACH CAN BE USED TO MAXIMIZE HIS/HER UTILITY FUNCTION. THE MODEL IS COMPARED WITH AN EXISTING ALGORITHM FOR IDENTIFYING ASSOCIATIONS USING A REAL DATASET PROVIDED BY THE PUBLIC PROSECUTOR S OFFICE OF REGIÓN DEL BIOBÍO-CHILE. THE RESULTS DEMONSTRATE THE PROPOSED MODEL S EFFECTIVENESS AND FLEXIBILITY IN GENERATING DIFFERENT ASSOCIATION ALTERNATIVES, A PARTICULARLY USEFUL FEATURE THAT CONTRIBUTES TO THE MORE EFFICIENT USE OF CRIMINAL INVESTIGATION RESOURCES.

THE DISARTICULATION OF CRIMINAL ORGANIZATIONS REDUCES THE RATES OF VICTIMIZATION AND INSECURITY IN THE POPULATION. ONE OF THE MAIN CHARACTERISTICS OF A CRIMINAL ORGANIZATION IS THE COHESION AMONG ITS MEMBERS. THIS INVESTIGATION PROPOSES A COHESION INDEX THAT ALLOWS IDENTIFYING QUICKLY IN BIG DATABASES INDIVIDUALS SUSPECT TO BELONG TO CRIMINAL ORGANIZATIONS AND FOCUS INVESTIGATION RESOURCES ON THEM. METHODS: TO OBTAIN THE INDEX, WE ANALYZE THE INFORMATION PROVIDED BY THE CRIMINAL ANALYSIS AND INVESTIGATIVE FOCUS SYSTEM FROM THE REGIONAL PUBLIC PROSECUTOR?S OFFICE IN BIOBÍO AND THE INVESTIGATION POLICE OF CHILE. FINDINGS: THE RESULTS SHOW THAT THE SUSPECTS WITH A HIGHER COHESION INDEX AND A HIGHER NUMBER OF CRIMINAL CASES COMMIT CRIMES ASSOCIATED WITH CRIMINAL ORGANIZATIONS.

ONE OF THE MOST COMMON METHODS USED IN THE SOCIAL NETWORK ANALYSIS OF CRIMINAL GROUPS IS NODE IMPORTANCE EVALUATION, WHICH FOCUSES ON THE LINKS BETWEEN NETWORK MEMBERS TO IDENTIFY LIKELY CRIME SUSPECTS. BECAUSE SUCH TRADITIONAL NODE EVALUATORS DO NOT TAKE FULL ADVANTAGE OF GROUP MEMBERS INDIVIDUAL CRIMINAL PROPENSITIES, A NEW EVALUATOR CALLED THE SOCIAL NETWORK CRIMINAL SUSPECT EVALUATOR (SNCSE) IS PROPOSED. SNCSE INCORPORATES MEMBERS INDIVIDUAL CRIMINAL PROPENSITIES INTO THE NODE IMPORTANCE EVALUATION AND EMPLOYS A NOVEL PERSPECTIVE BASED ON CONCEPTS OF HUMAN AND SOCIAL CAPITAL, AN EGO NETWORK STRUCTURE, AND AN ANALOGY BETWEEN SOCIAL INTERACTION AND FIELD THEORY. SNCSE IS APPLIED TO SOLVE TWO REAL-WORLD PROBLEMS. ITS EFFECTIVENESS IS COMPARED WITH THAT OF TRADITIONAL EVALUATORS. THE RESULTS SHOW THAT INTEGRATING CRIMINAL PROPENSITY INTO NETWORK ANALYSIS ENABLES THE MORE ACCURATE IDENTIFICATION OF KEY SUSPECTS COMPARED TO ALTERNATIVE EVALUATORS.

THIS WORKS SHOWS AN APPLICATION OF A CHURN MODEL FOR A COMPANY OF THE TELECOMMUNICATIONS INDUSTRY IN CHILE WITH TWO MAJOR MARKETS. CLUSTER ANALYSIS AND MULTIVARIATE LOGISTIC REGRESSION WERE USED AS DATA MINING METHODOLOGIES TO GENERATE THE CHURN MODEL. DATA BASE CONSIDERED THE PERIOD JANUARY 2009 AND JUNE 2011, AND VARIABLES SUCH AS PRODUCTS, DEMOGRAPHIC DATA, PAYMENT SYSTEMS, NUMBER AND TYPES OF COMPLAINTS FILLED WERE USED. TWO MODELS USING REGRESSION ANALYSIS WERE DEVELOPED WERE GENERATED FOR BOTH MARKETS. FOR THE CONCEPCIÓN MARKET THE MODEL ESTIMATES SUCCESSFULLY 71% OF THE TOTAL CASES, AND FOR TEMUCO MARKET WAS 72%. THE ABOVE INFORMATIONS ALLOWS THE COMPANY FOR THE PROPOSAL OF PROMOTIONAL EFFORTS AND TRAINING OF THE SALES FORCE PRIMARILY

EL COMPORTAMIENTO FRAUDULENTO EN EL CONSUMO DE AGUA POTABLE ES UN PROBLEMA IMPORTANTE QUE ENFRENTAN LAS EMPRESAS DE TRATAMIENTO DE AGUA DEBIDO A QUE GENERA PÉRDIDAS ECONÓMICAS SIGNIFICATIVAS. CARACTERIZAR CONSUMOS FRAUDULENTOS ES UNA TAREA COMPLEJA, BASADA PRINCIPALMENTE EN LA EXPERIENCIA, Y QUE PRESENTA EL DESAFÍO DE LA INCORPORACIÓN CONSTANTE DE NUEVOS CLIENTES Y LA VARIACIÓN EN EL CONSUMO MENSUAL. EN ESTA INVESTIGACIÓN, LAS TÉCNICAS DE MINERÍA DE DATOS SE UTILIZAN PARA CARACTERIZAR Y PREDECIR LOS CONSUMOS FRAUDULENTOS DE AGUA POTABLE. PARA ESTO, SE UTILIZÓ INFORMACIÓN HISTÓRICA RELACIONADA CON EL CONSUMO. LAS TÉCNICAS APLICADAS MOSTRARON UN ALTO RENDIMIENTO PREDICTIVO Y SU APLICACIÓN PERMITIRÁ ENFOCAR EFICIENTEMENTE LOS RECURSOS ORIENTADOS A EVITAR ESTE TIPO DE FRAUDE.

LA FUGA DE CLIENTES ES UN PROBLEMA RELEVANTE AL QUE ENFRENTAN LAS EMPRESAS DE SERVICIOS Y QUE LES PUEDE GENERAR PÉRDIDAS ECONÓMICAS SIGNIFICATIVAS. IDENTIFICAR LOS ELEMENTOS QUE LLEVAN A UN CLIENTE A DEJAR DE CONSUMIR UN SERVICIO ES UNA TAREA COMPLEJA, SIN EMBARGO, MEDIANTE SU COMPORTAMIENTO ES POSIBLE ESTIMAR UNA PROBABILIDAD DE FUGA ASOCIADA A CADA UNO DE ELLOS. ESTA INVESTIGACIÓN APLICA MINERÍA DE DATOS PARA LA PREDICCIÓN DE LA FUGA DE CLIENTES EN UNA EMPRESA DE DISTRIBUCIÓN DE GAS NATURAL, MEDIANTE DOS TÉCNICAS DE MACHINE LEARNING: REDES NEURONALES Y SUPPORT VECTOR MACHINE. LOS RESULTADOS MUESTRAN QUE MEDIANTE LA APLICACIÓN DE ESTAS TÉCNICAS ES POSIBLE IDENTIFICAR LOS CLIENTES CON MAYOR PROBABILIDAD DE FUGA PARA TOMAR SOBRE ESTAS ACCIONES DE RETENCIÓNOPORTUNAS Y FOCALIZADAS, MINIMIZANDO LOS COSTOS ASOCIADOS AL ERROR EN LA IDENTIFICACIÓN DE ESTOS CLIENTES.

UN REVESTIMIENTO MOLDEADO PARA PUERTAS ES UN TABLERO DE MADERA DE ALTA DENSIDAD QUE ES UTILIZADO COMO EL PRINCIPAL COMPONENTE EN LA FABRICACIÓN DE PUERTAS. PARA ASEGURAR SU COMERCIALIZACIÓN, SE DEBE CUMPLIR CON EXIGENTES NORMAS DE CALIDAD, SIENDO LA PRINCIPAL NORMA AQUELLA QUE MIDE LA FUERZA NECESARIA PARA DESPRENDER EL REVESTIMIENTO DE LA ESTRUCTURA DE UNA PUERTA. LOS ENSAYOS DE CALIDAD SON REALIZADOS CADA DOS HORAS Y SUS RESULTADOS SON OBTENIDOS LUEGO DE APROXIMADAMENTE CINCO HORAS. SI LOS RESULTADOS MUESTRAN QUE LOS REVESTIMIENTOS ESTÁN FUERA DEL ESTÁNDAR DE CALIDAD EXIGIDO, SE GENERAN PÉRDIDAS ECONÓMICAS DEBIDO A ESTE TIEMPO DE ESPERA. ESTA INVESTIGACIÓN PROPONE EL USO DE MINERÍA DE DATOS MEDIANTE TÉCNICAS DE MACHINE LEARNING PARA PREDECIR EN FORMA CONTINUA ESTA MEDIDA DE CALIDAD Y REDUCIR LAS PÉRDIDAS ECONÓMICAS ASOCIADAS A LA ESPERA DE LOS RESULTADOS. PARA LA APLICACIÓN DE MINERÍA DE DATOS, SE CREÓ UNA BASE DE DATOS EN BASE AL REGISTRO HISTÓRICO DE LAS VARIABLES DEL PROCESO PRODUCTIVO Y DE LOS ENSAYOS DE CALIDAD. LA METODOLOGÍA EMPLEADA ES EL DESCUBRIMIENTO DE CONOCIMIENTO EN BASES DE DATOS KDD (KNOWLEDGE DISCOVERY IN DATABASES). LA APLICACIÓN DE ESTA METODOLOGÍA PERMITIÓ IDENTIFICAR LAS PRINCIPALES VARIABLES QUE AFECTAN LA CALIDAD DE LOS REVESTIMIENTOS Y ENTRENAR CUATRO ALGORITMOS DE MACHINE LEARNING PARA PREDECIR SU CALIDAD. LOS RESULTADOS MUESTRAN QUE EL ALGORITMO QUE MEJOR PREDICE LA CALIDAD ES NEURAL NET Y PERMITEN DEMOSTRAR QUE LA IMPLEMENTACIÓN DEL ALGORITMO NEURAL NET REDUCIRÁ LAS PÉRDIDAS ECONÓMICAS ASOCIADAS A LA ESPERA DE LOS RESULTADOS DE LOS ENSAYOS DE CALIDAD.

LA PROGRAMACIÓN DE CITAS MÉDICAS ES UNA ACTIVIDAD DE GRAN IMPORTANCIA EN UN HOSPITAL, YA QUE SE DEBEN UTILIZAR DE FORMA EFICIENTE DIFERENTES CAPITALES, TANTO HUMANOS COMO MATERIALES. UNO DE LOS PROBLEMAS DE ESTE TRABAJO ES LA INASISTENCIA DE UN PACIENTE, LO QUE DISMINUYE LA EFICIENCIA DEL USO DE ESTOS RECURSOS. PARA HACER FRENTE A ESTO, DIVERSOS ESTUDIOS HAN PROPUESTO CONSIDERAR EL ?AUSENTISMO? PARA PROGRAMAR LAS CITAS MÉDICAS. SIN EMBARGO, PREDECIRLO ES UNA TAREA COMPLEJA. ESTA INVESTIGACIÓN PROPONE LA PREDICCIÓN DE LA NO ASISTENCIA A LA CITACIÓN PARA TRES ÁREAS MÉDICAS DEL HOSPITAL CLÍNICO REGIONAL DR. GUILLERMO GRANT BENAVENTE EN LA CIUDAD DE CONCEPCIÓN, CHILE. PARA ESTO SE ENTRENAN Y EVALÚAN CINCO ALGORITMOS DE MACHINE LEARNING. EL MEJOR MODELO ENTRENADO LOGRÓ SER UNA HERRAMIENTA PREDICTIVA DEL NIVEL DE AUSENTISMO DE UN PACIENTE PARA SU PRÓXIMA CONSULTA Y CARACTERIZAR A AQUELLOS PACIENTES CON MAYORES NIVELES DE AUSENTISMO.

LOGRAR ESTIMAR LA CANTIDAD DE DELITOS QUE SE COMETERÁN EN UNA DETERMINADA ZONA GEOGRÁFICA ES DE IMPORTANTE PARA LA GESTIÓN DE RECURSOS DESTINADOS A LA PREVENCIÓN DE DELITOS. ESTA INVESTIGACIÓN DESARROLLA DOS MODELOS PREDICTIVOS DE SERIES DE TIEMPO PARA LA PREDICCIÓN GEOGRÁFICA DE DELITOS CONTRA LA PROPIEDAD EN DOS COMUNAS DE CHILE, TALCAHUANO Y HUALPÉN. LOS MODELOS INVESTIGADOS FUERON REDES NEURONALES Y SARIMA. AMBOS MODELOS FUERON ENTRENADOS Y PROBADOS CON INFORMACIÓN PROPORCIONADA POR LA FISCALÍA REGIONAL DEL BIOBÍO, CHILE. LA INFORMACIÓN CONTIENE LOS DELITOS CONTRA LA PROPIEDAD COMETIDOS EN AMBAS COMUNAS ENTRE LOS AÑOS 2009 Y 2019. LOS MODELOS FUERON COMPARADOS MEDIANTE LAS MEDIDAS DE ERROR DE PRONÓSTICO MAPE, MAD Y MSE. LA COMPARACIÓN DE LOS RESULTADOS NO EVIDENCIAN DIFERENCIAS ESTADÍSTICAMENTE SIGNIFICATIVAS ENTRE LOS RESULTADOS DE AMBOS MODELOS.

OFFICE WORKERS SPEND MOST OF THEIR TIME INSIDE A BUILDING, AND AS A RESULT, PHYSICAL-ENVIRONMENTAL VARIABLES BEGIN TO PLAY A CRUCIAL ROLE IN THEIR PRODUCTIVITY AND PERFORMANCE. THIS STUDY ESTABLISHES A CONNECTION BETWEEN MACHINE LEARNING MODELS AND THE BEHAVIOR OF OCCUPANTS AND THE SELF- ASSESSED PRODUCTIVITY THEY EXHIBIT, THROUGH THE USE OF VARIOUS MODELS. THESE MODELS WERE IMPLEMENTED TO IDENTIFY AND COMPARE WHICH OF THEM BETTER ESTIMATE THIS BEHAVIOR, PARTICULARLY THE SELF-ASSESSED PRODUCTIVITY THAT INDIVIDUALS EXPERIENCE IN THEIR WORKPLACE. TO ACCOMPLISH THIS, PHYSICAL-ENVIRONMENTAL VARIABLES, AND THE PERCEPTIONS OF OCCUPANTS FROM VARIOUS OFFICE BUILDINGS IN THE CITY OF CONCEPCIÓN WERE COLLECTED. THIS STUDY SUCCESSFULLY COMPARES THE PERFORMANCE OF FOUR MACHINE LEARNING MODELS (DECISION TREE, K-NEAREST NEIGHBOR, BAYESIAN MODEL, AND NEURAL NETWORK). THEIR PERFORMANCE WAS MEASURED USING INDICATORS KNOWN AS ACCURACY, PRECISION, AND RECALL. THESE MODELS WERE APPLIED TO BOTH AN ORIGINAL DATABASE AND A BALANCED DATABASE, FOLLOWED BY A COMPARISON OF THE RESULTS OBTAINED. IT CAN BE ESTABLISHED THAT THERE IS A RELATIONSHIP BETWEEN PHYSICAL-ENVIRONMENTAL VARIABLES AND THE SELF-ASSESSED PRODUCTIVITY OF WORKERS. FURTHERMORE, IT CAN BE MENTIONED THAT THE NEURAL NETWORK IS THE MODEL THAT BEST DESCRIBES THIS RELATIONSHIP AND, THEREFORE, ACHIEVES THE HIGHEST PERFORMANCE. THIS STUDY PROVIDES AN APPROACH TO UNDERSTANDING OCCUPANT BEHAVIOR FROM A MACHINE LEARNING PERSPECTIVE.

BACKGROUND/OBJECTIVES: THEFT AND BURGLARY ARE TWO CRIMES AGAINST PROPERTY THAT HAVE A GREAT SOCIAL IMPACT. THEIR PREVENTION DRASTICALLY LOWERS VICTIMIZATION RATES AND THE FEELING OF INSECURITY IN THE POPULATION. THE OBJECTIVE OF THIS INVESTIGATION IS TO OBTAIN AN INDEX THAT ALLOWS THE PREDICTION OF REPEAT O?ENSES BY CRIMINALS IN THESE TYPES OF CRIMES, IN ORDER TO SUPPORT DECISION-MAKING WITH RESPECT TO PREVENTATIVE ACTIONS. METHODOLOGY: IN ORDER TO OBTAIN THE INDEX, A GROUP OF MACHINES LEARNING WAS TRAINED, WITH INFORMATION PROVIDED BY THE CRIMINAL ANALYSIS AND INVESTIGATIVE FOCUS SYSTEM (CAIFS) FROM THE REGIONAL PUBLIC PROSECUTOR?S O?CE IN BIOBÍO, CHILE. THE INFORMATION PROVIDED WAS FROM THEFTS AND BURGLARIES COMMITTED BETWEEN 2012 AND 2017 IN THE CITY OF CONCEPCIÓN. FINDINGS/APPLICATION: THE RESULTS SHOW A CHARACTERIZATION OF REPEAT O?ENDERS IN THESE TYPES OF CRIME AND A RECURRENCE INDEX THAT ALLOWS FOR A GREATER ASSERTIVENESS IN THE PREDICTION OF RECIDIVISM THAN THE METHOD THAT IS CURRENTLY BEING USED

SCHEDULING MEDICAL APPOINTMENTS PLAYS A FUNDAMENTAL ROLE IN MANAGING PATIENT FLOW AND ENSURING HIGH-QUALITY CARE. HOWEVER, NO-SHOWS CAN SIGNIFICANTLY DISRUPT THIS PROCESS AND AFFECT PATIENT CARE. TO ADDRESS THIS CHALLENGE, HEALTHCARE FACILITIES CAN ADOPT DIFFERENT STRATEGIES, INCLUDING OVERBOOKING IN MEDICAL CONSULTATIONS. WHILE THIS REDUCES THE RISK OF UNUSED SLOTS, IT CAN GENERATE ASSOCIATED COSTS AND AFFECT THE PERCEPTION OF SERVICE QUALITY. IN THIS ARTICLE, WE PROPOSE AN INTEGER LINEAR OPTIMIZATION MODEL THAT MAXIMIZES THE EXPECTED UTILITY OF A MEDICAL CENTER, CONSIDERING THE RISK OF NO-SHOWS AND OVERBOOKING. FOR THIS PURPOSE, MACHINE LEARNING IS USED TO ESTIMATE THE PROPENSITY OF EACH PATIENT TO ATTEND THEIR MEDICAL APPOINTMENT, USING REAL DATA FROM THREE MEDICAL SPECIALTIES OF A HOSPITAL. THE RESULTS OF THE APPLICATION DEMONSTRATE THE MODEL?S ABILITY TO ASSIGN APPOINTMENTS AND PERFORM OVERBOOKING EFFICIENTLY AND IN AN ORGANIZED MANNER, IMPLYING AN IMPROVEMENT IN THE UTILITY OF A MEDICAL CENTER AND A POSITIVE IMPACT ON THE PERCEPTION OF THE QUALITY OF CARE.