The　copper　prices　in　international　trade　markets　are　volatile.　An　accurate　copper　price　prediction　may　guide　commodity　trading　and　firm　profits　in　the　copper　industry.　In　this　paper,　a　hybrid　predictive　technique　combining　complex　network　and　traditional　artificial　neural　network　(ANN)　techniques　is　developed　for　copper　price　forecasting.　This　technique　first　transforms　the　original　price　time　series　to　a　price　volatility　network　(PVN)　and　extracts　the　volatility　characteristics　from　the　topological　structure　of　the　PVN.　After　the　original　data　are　reconstructed,　three　widely　used　ANN　techniques,　the　BPNN,　RBFNN,　and　ELM,　are　applied　to　forecast　the　future　copper　price.　To　examine　the　forecasting　performance　of　the　proposed　PVN-ANN　techniques,　the　published　data　of　copper　spot　prices　from　the　New　York　Commodity　Exchange　(COMEX)　are　used.　The　empirical　results　show　that　the　proposed　hybrid　PVN-ANN　techniques　can　obtain　a　favorable　prediction　effect　in　both　level　and　directional　predictions　compared　to　those　of　the　traditional　ANN　techniques.　This　result　clearly　demonstrates　the　effectiveness　of　the　proposed　hybrid　predictive　techniques　in　revealing　the　underlying　nonlinear　patterns　of　international　copper　prices.