Loading...

Minimum Rebar Price Forecast in Commodity Exchange with Machine Learning

Abtahi Forushani, Mahmoud | 2020

464 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53465 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Shadrokh Sikari, Shahram
  7. Abstract:
  8. In recent years, in addition to the stock market, a market has been created in Iran under the name of commodity exchange market. In this market, the product supplier announces some product specifications and buyers also announce their demand and bid price. The following two situations may occur: 1. The total amount of demand is less than or equal to the amount of supply.In this case all buyers receive the product at their bid price. Obviously, first all buyers announce a price lower than the base price so that if this happens, they can buy the required product at the lowest possible price. 2. If the supply is less than the demand, the market enters the competition. In this way, the new bid prices offered by the buyers are registered in the temporary registration system and then arranged in descending order. After the purchase requests are arranged from the highest price, all the requests are covered until the quantity of the offered goods is finished. Some purchase requests will not be answered in this case and some buyers will not participate in this transaction. The goal is to predict the lowest price at which you can buy the product and not be excluded from the transaction. In each transaction, the following items of product specifications are announced: 1. Supply rate 2. Base price 3. Delivery time 4. Type of contract 5. The value of the transaction Also, many criteria such as the lowest winning price in previous trades, the highest price offered in previous trades, the number of days to delivery, the price of dollars and gold, the total amount of demand, etc. can affect the minimum price. Due to the high number of these cases and also the uncertainty of the effectiveness of each criterion, the dissertation work is divided into two parts: determining the effective criteria and choosing from them and predicting the minimum winning price and choosing the best forecasting method for it.
  9. Keywords:
  10. Commodity Exchange ; Machine Learning ; Influential Factors ; Price Forecasting ; Competitive Market ; Minimum Price Prediction ; Freight Demand ; Good Supply

 Digital Object List

 Bookmark

No TOC