A progressive decline in soil fertility in taro (Colocasia esculenta L., Schott) production systems has led to reduced crop productivity and farm profitability, and is recognized as a major threat to soil and food security in Samoa. This paper reports the results of three years of field experimentation aimed at improving soil nutrient management practices and quantifying yield gaps in taro production systems. Experimental sites were established at two locations in Upolu Island to study the effects of crop nutrition on the soil nutrient balance, taro yield and nutrient recovery in harvested plant material (corm). Treatments included: (1) standard practice (no nutrients applied), (2) legume intercropping using Mucuna pruriens and Erythrina subumbrans, (3) application of NPK+S fertilizer, and (4) application of composted poultry manure. The evidence shows that appropriate nutrient budgeting is required to reduce current soil nutrient deficits and mitigate the loss of soil organic C, and that balanced crop nutrition should improve productivity and contribute to narrowing yield gaps. The paper also considered the need to develop a framework to guide nutrient recommendations for taro. This framework proposes that recommendations for N be derived from yield-to-N response functions (from which the most economic rate of N can be estimated), and that for other nutrients (P, K, Ca, Mg) recommendations be based on replacement. The replacement strategy requires the development of soil Indexes, which can be used to define the long-term nutrient management policy at a given site or field. This long-term policy is informed by soil analyses, and it will determine whether there is a need to build-up or maintain soil nutrients levels, or whether application can be omitted in some years because nutrient levels exist within a range that is satisfactory both from the agronomic and environmental perspectives.