Product pricing in TAC SCM using adaptive real-time probability of acceptance estimations based on economic regimes

Dynamic product pricing is a vital, yet non-trivial task in complex supply chains -- especially in case of limited visibility of the market environment. We propose to differentiate product pricing strategies using economic regimes. In our approach, we use economic regimes (characterizing market conditions) and error terms (accounting for customer feedback) to dynamically model the relation between available data and parameters of double-bounded log-logistic distributions assumed to be underlying daily offer prices. Given the parametric estimations of these price distributions, we then estimate offer acceptance probabilities using a closed-form mathematical expression, which is used to determine the price yielding a desired quota. The approach is implemented in the MinneTAC trading agent and tested against a price-following product pricing method in the TAC SCM game. Performance significantly improves. More customer orders are obtained against higher prices and profits more than double.