Nicko V.

BACKGROUND: Machine learning (ML) is the application of specialized algorithms to datasets for trend delin-eation, categorization, or prediction. ML techniques have been traditionally applied to large, highly dimensional databases. Gliomas are a heterogeneous group of primary brain tumors, traditionally graded using histopathologic features. Recently, the World Health Organization proposed a novel grading system for gliomas incorporating molecular characteristics. We aimed to study whether ML could achieve accurate prognostication of 2-year mortality in a small, highly dimensional database of patients with glioma.-METHODS: We applied 3 ML techniques (artificial neu-ral networks [ANNs], decision trees [DTs], and support vector machines [SVMs]) and classical logistic regression (LR) to a dataset consisting of 76 patients with glioma of all grades. We compared the effect of applying the algorithms to the raw database versus a database where only statistically significant features were included into the algo-rithmic inputs (feature selection).-RESULTS: Raw input consisted of 21 variables and achieved performance of accuracy/area (C.I.) under the curve of 70.7%/0.70 (49.9e88.5) for ANN, 68%/0.72 (53.4e90.4) for SVM, 66.7%/0.64 (43.6e85.0) for LR, and 65%/0.70 (51.6e89.5) for DT. Feature selected input consisted of 14 variables and achieved performance of 73.4%/0.75 (62.9e87.9) for ANN, 73.3%/0.74 (62.1e87.4) for SVM, 69.3%/0.73 (60.0e85.8) for LR, and 65.2%/0.63 (49.1e76.9) for DT.-CONCLUSIONS: We demonstrate that these techniques can also be applied to small, highly dimensional datasets. Our ML techniques achieved reasonable performance compared with similar studies in the literature. Although local databases may be small versus larger cancer repositories , we demonstrate that ML techniques can still be applied to their analysis; however, traditional statistical methods are of similar benefit.

Author: Sandip Panesar

Resumen Los estados financieros básicos como el balance general o estado de situación financiera, estado de resultados o de actividades según corresponda, el estado de variaciones en el capital contable o patrimonio contable y el estado de flujo de efectivo, formulados con base en las normas de información financiera (NIF), así como información de carácter cualitativo de una entidad económica, proporcionan elementos para realizar el análisis de estados financieros, aplicando los métodos y técnicas para tal efecto; proporcionando información útil sobre los aspectos de liquidez, endeudamiento, rentabilidad, cobertura y actividad, identificando así las fortalezas y debilidades y disponer de elementos para la toma de decisiones. Abstract The basic financial statements as the balance sheet or statement of financial position, income statement or activities as appropriate, the statement of changes in stockholders' equity or equity accounting and cash flow statement, formulated based on financial reporting standards (NIF) and qualitative information of an economic entity, provide elements for the analysis of financial statements using the methods and techniques for this purpose; provide us useful

...We provide some exercises in Part I, which can be done mostly by pen and
paper. For Part II, we provide programming tutorials (jupyter notebooks)
to explore some properties of the machine learning algorithms we discuss
in this book.
We appreciate that Cambridge University Press strongly supports our
aim to democratize education and learning by making this book freely
available for download at
https://mml-book.com
where tutorials, errata, and additional materials can be found. Mistakes
can be reported and feedback provided using the preceding URL.

RESUMEN Es importante prevenir y conocer los costos de una casa que está en venta al dirigirse a una zona en particular. Se usó una base de datos de precios de venta de casas en Lima Moderna, Este y Sur, y otras características de estas. El fin de este proyecto es brindar información de ayuda para las personas que estén en la necesidad de adquirir una propiedad en Lima Moderna, Este y Sur. Al analizar la distribución del precio de las casas, se vio que esta no era normal. Se aplicó la transformación de Johnson para poder cumplir los supuestos de un modelo de Regresión. Se utilizó la nueva variable respuesta para aplicar un análisis de regresión lineal y un análisis de regresión espacial. Se vio las diferencias entre ambos modelos y se determinó que el mejor modelo de estimación era el espacial, es decir, considerando variables que se mueven en el espacio. Se descartaron las variables Jardín y Antigüedad y se obtuvo un modelo explicativo para el precio de las casas en Lima Moderna, Este y Sur con las demás variables.
ABSTRACT It is important to prevent and know the costs of a home that is for sale when heading to a particular area. A database of sale prices of houses in Modern Lima, East and South, and other characteristics of these were used. The purpose of this project is to provide help information for people who are in need of acquiring a property in Modern Lima, East and South. When analyzing the distribution of the price of the houses, it was seen that this was not normal. Johnson's transformation was applied in order to fulfill the assumptions of a Regression model. The new response variable was used to apply a linear regression analysis and a spatial regression analysis. The differences between the two models were found and the best estimation model was determined to be spatial, is considering variables that move in space. The variables Garden and Antiquity were discarded and an explanatory model was obtained for the price of the houses in Modern Lima, East and South with the other variables.