Method for forecasting housing prices using a dynamic error correction model
A system and method for forecasting a price of a property in a first housing sub-market based on data related to a second housing sub-market are described. A price index is derived for the second housing sub-market, and an error correcting function is calculated for the first housing sub-market. A price index for the first housing sub-market is derived from the second sub-market price index and the error correcting function. An estimate of the price of the price of the property in the first housing sub-market is then provided. The estimate of the price can be used as the basis for an economic decision.
1. A computer-implemented method for forecasting property prices, the method comprising:
retrieving first historical transaction data of a first property sub-market from a first database;
retrieving second historical transaction data of a second property sub-market from a second database;
calculating, by at least one computer processor, a second price index of the second property sub-market based on the retrieved second historical transaction data;
calculating, by the at least one computer processor, an error correction function based on the retrieved first historical transaction data and the calculated second price index;
calculating, by the at least one computer processor, a first price index based on the calculated error correction function and the calculated second price index;
forecasting a price of property in the first property sub-market based on the calculated first price index; and
storing the forecasted price in a memory device.
2. The computer-implemented method of claim 1 , wherein the retrieved second historical transaction data includes more transactions than the retrieved first historical transaction data.
3. The computer-implemented method of claim 1 , wherein the first property sub-market and second property sub-market are housing sub-markets.
4. The computer-implemented method of claim 3 , wherein the first property sub-market is a condominium sub-market and the second property sub-market is a single-family home sub-market.
5. The computer-implemented method of claim 1 , wherein the first price index is calculated as derivations from the calculated second price index.
6. The computer-implemented method of claim 1 , wherein the calculated error correction model is associated with a difference between the first price index and the second price index.
7. The computer-implemented method of claim 1 , wherein calculating the error correction function is further based on at least one refinance bias.
8. A non-transitory computer-readable medium storing program instructions, which, when executed on at least one processor, causes the at least one processor to perform a method for generating a first price index for a first property sub-market based on first historical transaction data from the first property sub-market and second historical transaction data from a second property sub-market, the method comprising:
calculating a second price index of the second property sub-market based on the second historical transaction data;
calculating an error correction function based on the first historical transaction data and the second price index;
calculating the first price index based on the error correction function and the second price index;
forecasting a price of property in the first property sub-market based on the first price index; and
storing the forecasted price in a memory device.
9. The computer-readable medium of claim 8 , wherein the second historical transaction data includes more transactions than the first historical transaction data.
10. The computer-readable medium of claim 8 , wherein the first property sub-market and second property sub-market are housing sub-markets.
11. The computer-readable medium of claim 10 , wherein the first property sub-market is a condominium sub-market and the second property sub-market is a single-family home sub-market.
12. The computer-readable medium of claim 8 , wherein the first price index is calculated as derivations from the second price index.
13. The computer-readable medium of claim 8 , wherein the error correction model is associated with a difference between the first price index and the second price index.
14. The computer-readable medium of claim 8 , wherein calculating the error correction function is further based on at least one refinance bias.
15. A system for forecasting a price of property, the system comprising:
a first database storing first historical transaction data about a first property sub-market;
a second database storing second historical transaction data about a second property sub-market;
a computing platform configured to:
calculate a second price index of the second property sub-market based on the second historical transaction data;
calculate an error correction function based on the first historical transaction data and the second price index;
calculate the first price index based on the error correction function and the second price index; and
forecast a price of property in the first property sub-market based on the first price index; and
an input/output device configured to provide the forecasted price to at least one user.
16. The system of claim 15 , wherein the second historical transaction data includes more transactions than the first historical transaction data.
17. The system of claim 15 , wherein the first property sub-market and second property sub-market are housing sub-markets.
18. The system of claim 17 , wherein the first property sub-market is a condominium sub-market and the second property sub-market is a single-family home sub-market.
19. The system of claim 15 , wherein the first price index is calculated as derivations from the second price index.
20. The system of claim 15 wherein the error correction model is associated with a difference between the first price index and the second price index.
21. The system of claim 15 , wherein calculating the error correction function is further based on at least one refinance bias.
22. The system of claim 15 , wherein the first database is different from the second database.