{"id":55,"date":"2022-04-03T22:38:02","date_gmt":"2022-04-03T22:38:02","guid":{"rendered":"https:\/\/pfr.com\/WP1\/?page_id=55"},"modified":"2026-04-24T18:34:22","modified_gmt":"2026-04-24T18:34:22","slug":"price-wizard","status":"publish","type":"page","link":"https:\/\/pfr.com\/WP1\/products\/price-wizard\/","title":{"rendered":"Price Wizard"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n\n

Price Wizard\u2122 <\/strong>is a suite of industry\u2010scoped and multi\u2010factor neural network equity models<\/strong> that were pre\u2010trained to convert recently reported company fundamentals<\/strong> into a current estimated market price.<\/strong> It uses no future growth expectations, analyst estimates, or price momentum. In fact, Price Wizard input factors do not include price in any form, past or present. This program automatically performs an appraisal by simultaneously using common stores of value like earnings, cash flow, book, and dividends, along with critical modifiers such as industry, margins, debt, interest rates, and inflation, in order to determine a price.<\/p>\n\n\n\n

How It Works:<\/strong><\/h2>\n\n\n\n

Neural Networks<\/h3>\n\n\n\n

Our equity-pricing model uses neural networks<\/strong><\/a> to learn how a stock\u2019s fundamental balance sheet data has been translated to a market price in the past, within the context of its industry group and economic sector. Common factors such as earnings, sales, margins, dividends, debt, book value, and cash flow are used to train our networks. A separate network has been created for each economic sector, and is used to estimate prices going forward.<\/p>\n\n\n\n

How Are Stock Prices Determined?<\/h3>\n\n\n\n

The latest quarter\u2019s information is fed into the neural net models to estimate current fair market prices for any stock. Our processing is carried out once a month and the results are delivered as a spreadsheet or as a database for use with TradeStation. These values can then be used in many ways.<\/p>\n\n\n\n

Price Disparity is Predictive<\/h3>\n\n\n\n
\n
\n

Any disparity between estimated prices and market prices is predictive of average future price trends six to twelve months in the future, and so has a multitude of uses. Price Wizard<\/strong>\u2122 prices lead to improved stock screening, aggregate estimates of ETF value, estimates of asset class value, risk management, and building internal index portfolios. During the 2000 stock market bubble, our model helped avoid being seduced by the herd (see picture).<\/p>\n<\/div>\n\n\n\n

\n
\"\"\/<\/figure>\n<\/div>\n<\/div>\n\n\n\n

Price Aggregates<\/h3>\n\n\n\n

Each month Parallax aggregates Price Wizard prices by sector, industry, market cap, and asset style. We also estimate the median valuation of all US equities. When the median valuation is beyond 5%, the entire market usually responds over the next three months. Below are some example aggregate valuation results:<\/p>\n\n\n

\n
\"\"\/
Industries in the red are overvalued, while those in the green are undervalued.<\/em><\/figcaption><\/figure>\n<\/div>\n\n
\n
\"\"\/<\/figure>\n<\/div>\n\n
\n
\"\"\/<\/figure>\n<\/div>\n\n\n

Price Wizard\u2122 on Bloomberg<\/strong> or FMP<\/h2>\n\n\n\n

You can get our international equity valuation application, Price Wizard<\/strong>, as an enhancement to the user’s Bloomberg Terminal<\/strong> directly from our online store<\/a>. The Bloomberg platform was chosen as a primary data source for our products because of its exclusive access to worldwide financial data, and because of its position as the leading institutional platform. For the first time ever, subscribers will be able to value equities anywhere in the world using our neural network model! Our product is written using Microsoft\u2019s .NET library, the C# programming language, and then linked to Bloomberg data servers through the Bloomberg desktop API. We also recently added full support for Financial Modeling Prep’s APIs (FMP). They provide a wide range of data at a lower price point that may be more suitable to smaller management businesses. <\/p>\n\n\n