REMV Market Report July, 2019

In this notebook we compare the accuracy of an OLS, NN (R:neuralnet), & XGBoost model predict zip code median income using use median home values.

In this notebook we compare performance of 3 Models on predicting historic interest rates in the United States. Although ARIMA and ETS are less computationally expensive to implement, the LSTM significantly outperforms ARIMA and ETS on minimizing our error metric (MAE).

In this project we’ll use real estate listing description data from the CRMLS to predict the final sale price of a home. While ultimately a property’s physical characterisitics (bed, bath, squarefootage, location) are the primary determinants of a sale, perhaps a well phrased listing description may attract more interest in a home, which means more competing offers and a higher sale price.

This notebook conducts an Exploratory Data Analysis (EDA) of energy data then performs a forecast using ETS (Error Trend Seasonality) and ARIMA (Autoregressive Integrated Moving Average) to forecast residential energy use.

This strategy uses three separate indicators and five separate signals. The strategy requires both the threshold of the DVO_2_126 indicator to be under 20 and the SMA50 to be greater than the SMA200. The strategy sells when the DVO_2_126 crosses above 80, or the SMA50 crosses under the SMA200

In this project we use First Name, Last Name, and Census Ethnicity Data from the American Community Survey to predict a person’s ethnicity.

Inspecting SB County Deed and Mortgage Data